DESC:TECHNICAL FIELD
The present disclosure relates to an analysis of a basmati rice grain sample. More particularly, the disclosure relates to a system and a method for detection of inter and intra adulteration in the basmati rice grain sample using low and high-magnification images.
BACKGROUND
Assessing the surface quality of pre-processed Basmati rice grains hold significant importance in determining market viability, storage durability, processing integrity, and overall customer satisfaction. Within the agricultural sector, grading Basmati rice grains stands as a critical yet challenging task, demanding specialized expertise. The grading process involves identifying grain variations, detecting different impurities, and gauging the quantities of the grains to forecast the quality of Basmati rice.. Henceforth in the text, grain refers to milled Basmati rice kernel.
For example, rice serves as the staple food in the South Asian continent, particularly dominating consumption in India, where it is broadly categorized into two main types: Basmati and Non-Basmati. Basmati rice, characterized by its long, slender grains, and pleasant aroma post-cooking, stands in contrast to the shorter and less aromatic non-Basmati variety. The subtle differences in length, often just a few millimeters, are imperceptible to the naked eye. Unfortunately, this discrepancy opens the door for unscrupulous shopkeepers to frequently adulterate Basmati rice with its non-Basmati counterparts, a practice that often escapes the notice of unsuspecting customers. The adulterated rice not only compromises the distinctive qualities of Basmati but also exhibits a heightened chalkiness, manifesting as milky-white portions on rice kernels due to irregular starch granule spacing. Furthermore, to meet the ever-increasing demand for Basmati rice, novel crossbred varieties of Basmati have been bred by the plant breeders. These are called evolved Basmati and are apt for intensive cultivation. Accounting for the evolved Basmati, India has 34 varieties of Basmati rice (as per Indian Seed Act 1966) whose market price varies from approximately INR 35/kg to as high as INR 200/kg and the size varying from 6 mm up to 9.77 mm (Pusa 1121). The traditional Basmati varieties gain high premium compared to their evolved counterparts due the consumer preference, which results in brand equity. Additionally, there are poorer quality non-aromatic long grain rice varieties in the market which have same visual and textural appearance. The similarity in appearance of different varieties (and therefore the difficulty in distinguishing them), and the significant price difference between leads to both intra-basmati rice and inter-rice adulteration by fraudulent dealers.
Traditional approaches for evaluating surface quality and adulteration which lack consistency and heavily rely on subjective judgment, are laborious. Current methodologies either separate undamaged grains from those with defects without further categorization or focus solely on distinguishing between various grain types. The main limitation of these conventional methods lies in their dependence on manual feature extraction, a field-specific process that is arduous, time-consuming, and error-prone. This reliance on manual labor contributes to the error-prone nature of traditional human-led quality assessment in grain evaluation, influenced by biases like recency and confirmation bias, leading to inaccuracies. The manual nature of the process is also time-consuming. Despite efforts to automate grain grading, challenges with costly infrastructure and significant initial investments make them economically impractical for widespread use in agro-based applications, impacting overall usability.
Therefore, there is a need for a system and method to overcome the limitations of the conventionally available methods for the detection of adulteration in a grain sample.
SUMMARY
In an aspect, a system to detect inter and intra-adulteration in a Basmati rice grain sample placed in a grooved plate is disclosed. The system includes an apparatus that includes one or more imaging devices that are configured to capture (i) one or more low-magnification images of the grooved plate and one or more high-magnification images of individual grains. The processing circuitry that is coupled to the apparatus and configured to (i) pre-process the one or more low magnification images to generate one or more pre-processed images, (ii) align the grooved plate in the one or more pre-processed images by way of an image warping technique to extract one or more images of the individual grain by way of a classifier model, (iii) pre-process the extracted one or more images of the individual grain, and (iv) determine a set of physical features associated with the individual grain from the extracted one or more images of the individual grain, wherein each of the individual grains are identified as a specific species of the grain, and (v) generate a report based on identification of the individual grain as the specific species of the grain.
In some aspects of the present disclosure, the one or more imaging devices include a plurality of lenses such that the plurality of lenses is adapted to provide an optical resolution in a range of 1 micrometer (µm) per pixel to 125 micrometer (µm) per pixel.
In some aspects of the present disclosure, to pre-process the one or more low magnification images the processing circuitry is configured to convert the image into a greyscale image, convert greyscale media into a binary image by way of a thresholding technique to identify the grooved plate in the binary image, and extract one or more corners of the grooved plate by way of edge detection from the binary image,.
In some aspects of the present disclosure, the apparatus further includes a user device such that the processing circuity is configured to transmit the generated report to the user device.
In some aspects of the present disclosure, the apparatus includes one or more motors coupled to the grooved plate such that the one or more motors is configured to enable vibration, and back and forth oscillation of the grooved plate for even distribution of the grain sample onto the grooved plate.
In some aspects of the present disclosure, the apparatus including the grooved plate exhibits a dual-tone composition: a central region, housing the grids, is of a single dark color, and the surrounding area is of a contrasting light color.
In some aspects of the present disclosure, the apparatus includes a dispenser coupled to at least one motor of the one or more motors, such that the dispenser is activated by way of at least one motor of the one or more motors for dispensing the grain sample onto the grooved plate.
In some aspects of the present disclosure, the apparatus includes a plurality of illuminators adapted to illuminate the grooved plate.
In some aspects of the present disclosure, the apparatus includes a plurality of calibration marks disposed on top and bottom faces of the grooved plate such that the plurality of calibration marks enables calibration of the one or more imaging devices with respect to the grooved plate.
In some aspects of the present disclosure, the processing circuitry implements the classifier model such that to train the classifier model, the processing circuitry is configured to (i) receive one or more high-magnification images of the individual grain identified as a specific species of the grains, (ii) pre-process the one or more high magnification images to generate a set of pre-processed images, and (iii) train the classifier model by way of the set of pre-processed images, such that the classifier model is optimized by (a) scheduling a learning rate of the classifier model using a decay function and (b) applying model fitting to the classifier model by way of early stops and checkpoint callbacks.
In some aspects of the present disclosure, a method for detecting an inter and intra adulteration in a grain sample placed in a grooved plate is disclosed. The method includes a step capturing of one or more low magnification images of the grooved plate. Further, the method includes pre-processing of the one or more low magnification images to generate one or more pre-processed images. The method further includes the aligning of the grooved plate in the one or more pre-processed images by way of an image warping technique to extract one or more images of individual grain by way of a classifier model. The method further includes the pre-processing of the one or more images of the individual grain extracted by way of the processing circuitry. The method further includes determining a set of physical features associated with the individual grain from the extracted one or more images of the individual grain, such that each of the individual grains is identified as a specific species of the grain by way of the processing circuitry.
In some aspects of the present disclosure, the one or more imaging devices comprising a plurality of lenses such that the plurality of lenses is adapted to provide an optical resolution in a range of 1 micrometer (µm) per pixel to 125 micrometer (µm) per pixel.
In some aspects of the present disclosure, to pre-process the one or more low magnification images, the processing circuitry is configured to convert the image into a greyscale image, convert the greyscale media into a binary image by way of a thresholding technique to identify the grooved plate in the binary image, and extract one or more corners of the grooved plate by way of edge detection from the binary image.
In some aspects of the present disclosure, the method further includes capturing by way of the one or more imaging devices one or more high magnification images of individual grain. The method further includes pre-processing by way of the processing circuitry the one or more high magnification images of individual grain to generate a set of pre-processed images. The method further includes training by way of the processing circuitry the classifier model via the set of pre-processed images wherein the classifier model is optimized by (a) scheduling a learning rate of the classifier model using a decay function and (b) applying model fitting to the classifier model by way of early stops and checkpoint callbacks.
In some aspects of the present disclosure, the method further includes generating a report based on the identification of the individual grain as the specific species of the grain.
In some aspects of the present disclosure, the method further includes transmitting the generated report to a user device.
BRIEF DESCRIPTION OF DRAWINGS
The above and still further features and advantages of aspects of the present disclosure become apparent upon consideration of the following detailed description of aspects thereof, especially when taken in conjunction with the accompanying drawings, and wherein:
FIG. 1A illustrates a block diagram of a system for detection of inter and intra adulteration in a grain sample, in accordance with an aspect of the present disclosure;
FIG. 1B illustrates a front view of an apparatus of the system of FIG. 1A, in accordance with an embodiment of the present disclosure;
FIG. 1C illustrates a perspective view of a grooved plate of the system of FIG. 1A, in accordance with an aspect of the present disclosure;
FIG. 1D illustrates block diagram of an information processing apparatus of the system of FIG. 1A, in accordance with an aspect of the present disclosure;
FIG. 2 illustrates a flow chart of a method for detecting an inter and intra adulteration in a grain sample, in accordance with an exemplary aspect of the present disclosure; and
FIG. 3A and 3B illustrate a flow chart and a processed image, respectively for determination of the inter and intra adulteration in a rice grain sample, in accordance with an exemplary aspect of the present disclosure.
To facilitate understanding, reference numerals have been used, where possible, to designate elements common to the figures in accordance with an exemplary aspect of the present disclosure.
DETAILED DESCRIPTION
This section is intended to provide an explanation and description of various possible aspects of the present disclosure. The aspects used herein, and the various features and advantageous details thereof are explained elaborately with reference to the non-limiting aspects that are illustrated in the accompanying drawing/s and detailed in the following description. The examples used herein are intended only to facilitate an understanding of ways in which the aspects may be practiced and to enable the person skilled in the art to practice the aspects used herein. Also, the examples/aspects described herein should not be construed as limiting the scope of the aspects herein.
The various aspects including the example aspects are now described elaborately with reference to the accompanying drawings, in which the various aspects of the disclosure are shown. The disclosure may, however, be embodied in different forms and should not be construed as limited to the aspects set forth herein. Rather, these aspects are provided so that this disclosure conveys the scope of the disclosure to those skilled in the art. In the drawings, the sizes of components may be exaggerated for clarity.
The subject matter of example aspects, as disclosed herein, is described with specificity to meet statutory requirements. However, the description itself is not intended to limit the scope of this patent. Rather, the inventor/inventors have contemplated that the subject matter might also be embodied in other ways, including different features or combinations of features similar to the ones described in this document, in conjunction with other technologies. Generally, the various aspects including the example aspects relate to a low and high-magnification system and method for detection of inter and intra adulteration in the grain sample.
The aspects herein and the various features and advantageous details thereof are explained more fully with reference to the non-limiting aspects that are illustrated in the accompanying drawings and detailed in the following description. Descriptions of well-known components and processing techniques are omitted so as to necessarily obscure the aspects herein. The examples used herein are intended merely to facilitate an understanding of ways in which the aspects herein may be practiced and to further enable those of skill in the art to practice the aspects herein. Accordingly, the examples should not be construed as limiting the scope of the aspects herein.
The term “sample” refers to a Basmati rice grain to be tested.. Aspects of the present disclosure are intended to include or otherwise cover any type of Basmati rice grain, without deviating from the scope of the present disclosure.
The term “parameters” refers to one or more physical features of the sample. The parameters may include but are not limited to primary features such as the length of the grain, a width of the grain, shape, texture, color, color gradients, surface parameters, and secondary features such as striped, chalky, green, broken, discolored, or any other surface damage and the like. Aspects of the present disclosure are intended to include or otherwise cover any type of physical feature of the grain, without deviating from the scope of the present disclosure.
FIG. 1A illustrates a block diagram of a system 100 for detection of inter and intra adulteration in a grain sample, in accordance with an aspect of the present disclosure. Specifically, the system 100 may be configured to utilize one or more hardware components to realize a low and high-magnification system 100 that facilitates in detection of inter and intra adulteration of the grain sample. Specifically, the system 100 may be configured to identify admixtures within the grain sample, such as inorganic extraneous matter and different variants of paddy grains, as well as undesirable grains like under-milled, red-striped, chalky, green, broken, fragmented, and discolored damaged grains. Examples of the grain sample may include, but are not limited to any type of Basmati rice, rice, maize, wheat, oats, cornmeal, barley, rye, amaranth, quinoa, spelt, teff, farro, sorghum, millet, and the like. Aspects of the present disclosure are intended to include or otherwise cover any type of the Basmati rice grain, without deviating from the scope of the present disclosure.
The system 100 may include an apparatus 102 and an information processing apparatus 118. The apparatus 102 and the information processing apparatus 118 may be communicatively coupled to each other by way of a communication network 138. The apparatus 102 may include one or more imaging devices 104. Each of the one or more imaging devices 104 may include a plurality of lenses 108 (hereinafter referred to as “the lenses 108”). The lenses 108 may be adapted to provide an optical resolution in a range of 1 micrometer (µm) per pixel to 125 µm per pixel.
In some aspects of the present disclosure, the information processing apparatus 118 may be a network of computers, a framework, or a combination thereof, that may provide a generalized approach to create a server implementation. In some aspects of the present disclosure, the information processing apparatus 118 may be a server. Examples of the information processing apparatus 118 may include but are not limited to, personal computers, laptops, mini-computers, mainframe computers, any non-transient and tangible machine that can execute a machine-readable code, cloud-based servers, distributed server networks, or a network of computer systems. The information processing apparatus 118 may be realized through various web-based technologies such as, but not limited to, a Java web framework, a .NET framework, a personal home page (PHP) framework, JavaScript, React, Python, PyQt, Qt, and C/C++ or any other web application framework. Aspects of the present disclosure are intended to include or otherwise cover any type of the web-based technologies including known, related art, and/or later developed web-based technologies. The information processing apparatus 118 may include processing circuitry 120 and a database 124.
In some aspects of the present disclosure, the processing circuitry 120 may include suitable logic, instructions, circuitry, interfaces, and/or codes for executing various operations of the system 100. Examples of the processing circuitry 120 may include, but are not limited to, an ASIC processor, a RISC processor, a CISC processor, a FPGA, and the like. Aspects of the present disclosure are intended to include or otherwise cover any type of the processing circuitry including known, related art, and/or later developed processing circuitry.
In some aspects of the present disclosure, the processing circuitry 120 may be configured to extract a first set of parameters from predefined data and train a classifier model based on the first set of parameters of the grain sample. In some aspects of the present disclosure, the processing circuitry 120 may be configured to process the input data, by way of one or more Machine Learning (ML) and Artificial Intelligence (AI) techniques. For example, the one or more ML and AI techniques may include, but not limited to, Supervised Learning, Semi-supervised learning, Reinforcement Learning, Deep Learning, Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Natural Language Processing (NLP), Principal Component Analysis (PCA), Text Analysis, Speech Recognition, Computer Vision, Image Recognition, Object Detection, Expert Systems, Rule-Based Systems, Genetic Algorithms, Evolutionary Algorithms, Robotics, Robotic Process Automation (RPA), Autonomous Robots, Knowledge Representation and Reasoning, Ontologies, Clustering Algorithms (e.g., K-Means, Hierarchical Clustering), Recommender Systems, Collaborative Filtering, Content-Based Filtering, Fuzzy Logic, Fuzzy Systems, Monte Carlo Tree Search, Swarm Intelligence, Ant Colony Optimization, Particle Swarm Optimization, Anomaly Detection and the like. Aspects of the present disclosure are intended to include and/or otherwise cover any type of the ML and AI techniques, without deviating from the scope of the present disclosure. The ML and AI techniques may require training of one of, a deep learning model, machine learning model, federated learning model, or the like. Aspects of the present disclosure are intended to include and/or otherwise cover training of any model that may be suitable for prediction of parameters of the biological grain sample, without deviating from the scope of the present disclosure.
In some aspects of the present disclosure, the processing circuitry 120 may be configured to implement a deep learning model using one or more transfer learning techniques. In some aspects of the present disclosure, to train the set of deep learning models, the processing circuitry 120 may be configured to employ a supervised and/or semi-supervised learning technique. The processing circuitry 120 may use supervised or semi-supervised learning techniques to divide multiple training images from a labeled training dataset (typically representing grain sample features) into overlapping parameters of the grain sample.
In some aspects of the present disclosure, the processing circuitry 120 may further be configured to shuffle the parts of each training image and may determine a spatial relationship, contextual information, and an intrinsic structure between each part of each training image using one or more supervised or semi-supervised learning techniques. The processing circuitry 120 through training of the set of deep learning models may determine grain sample information. The labelled training dataset may include a diverse range of cases, covering various parameters and anatomical variations, which may lead to robust and generalized training. Further, the available labelled training dataset used for training the deep learning model may remove the dependence on specifically developed datasets for training. In some aspects of the present disclosure, the processing circuitry 120 may further be configured to fine-tune the set of trained deep learning models on a first dataset. By fine-tuning the set of deep learning models, the processing circuitry 120 may enhance the ability of the set of trained deep learning models to enhance the quality of image for a better estimation of the geometric and surface parameters or grain features.
In some aspects of the present disclosure, the database 124 may be configured to store the logic, instructions, circuitry, interfaces, and/or algorithms of the processing circuitry 120 for executing various operations. The database 124 may be configured to store therein data associated with users registered with the system 100. The database 124 may be configured to store one or more training datasets and/or one or more deep learning models that may be used either by the classification model and/or the determination of user specific parameters. In some aspects of the present disclosure, the database 124 may be further configured to store the data or the representations of the state of the user that may be generated by the information processing apparatus 118. Aspects of the present disclosure are intended to include and/or otherwise cover any type of the database 124 including known, related art, and/or later developed database, without deviating from the scope of the present disclosure. In some aspects of the present disclosure, the operations executed by the processing circuitry 120 of the information processing apparatus 118 may be executed by way of a central processing unit (CPU) 119 (as shown later in FIG. 1B) of the apparatus 102.
In some aspects of the present disclosure, the communication network 138 may include suitable logic, circuitry, and interfaces that may be configured to provide a plurality of network ports and a plurality of communication channels for the transmission and reception of data related to operations of various entities of the system 100. Each network port may correspond to a virtual address (or a physical machine address) for transmission and reception of the communication data. For example, the virtual address may be an Internet Protocol Version 4 (IPV4) (or an IPV6 address) and the physical address may be a Media Access Control (MAC) address. The communication network 138 may be associated with an application layer for the implementation of communication protocols based on one or more communication requests from a user device 128 and the information processing apparatus 118. The communication data may be transmitted or received via the communication protocols. Examples of the communication protocols may include, but are not limited to, Hypertext Transfer Protocol (HTTP), File Transfer Protocol (FTP), Simple Mail Transfer Protocol (SMTP), Domain Network System (DNS) protocol, Common Management Interface Protocol (CMIP), Transmission Control Protocol and Internet Protocol (TCP/IP), User Datagram Protocol (UDP), Long Term Evolution (LTE) communication protocols, or any combination thereof. Aspects of the present disclosure are intended to include or otherwise cover any type of communication protocols including known, related art, and/or later developed communication protocols.
In some aspects of the present disclosure, the communication data may be transmitted or received via at least one communication channel of a plurality of communication channels in the communication network 138. The communication channels may include but are not limited to, a wireless channel, a wired channel, or a combination of wireless and wired channels thereof. The wireless or wired channel may be associated with a data standard which may be defined by one of a Local Area Network (LAN), a Personal Area Network (PAN), a Wireless Local Area Network (WLAN), a Wireless Sensor Network (WSN), Wireless Area Network (WAN), Wireless Wide Area Network (WWAN), a metropolitan area network (MAN), a satellite network, the Internet, a fiber optic network, a coaxial cable network, an infrared (IR) network, a radio frequency (RF) network, and a combination thereof. Aspects of the present disclosure are intended to include or otherwise cover any type of communication channel, including known, related art, and/or later developed technologies.
FIG. 1B illustrates a front view of an apparatus 102 of the system 100 of FIG. 1A, in accordance with an embodiment of the present disclosure. The apparatus 102 may include a user device 128, a user device holder 129, a dispenser 101, a grooved plate setup 103 having a grooved plate 103a, one more imaging devices 104 (hereinafter referred to as “the imaging devices”), one or more motors 105 (hereinafter interchangeably referred to and designated as “the motors 105”) of which first through third motors 105a-105c are shown, a plurality of illuminators 106 of which first and second illuminators 106a and 106b are shown, and a plurality of calibration marks 134 (hereinafter referred to as “the calibration marks 134”).
The apparatus 102 may be utilized for capturing one or more images and/or one or more videos of the grain sample and providing information associated with the grain sample to and the information processing apparatus 118 for processing. The apparatus 102 and the information processing apparatus 118 may be communicatively coupled to each other through the communication network 138. In some aspects of the present disclosure, the apparatus 102 and the information processing apparatus 118 may be connected to each other through one or more wired and/or wireless communication networks established therebetween.
In some aspects, a portable and detachable grooved plate 103a within the system 100, may be configured to align grains in a grid arrangement. Preferably, the grooved plate 103a may be a transparent grooved plate. This grooved plate may facilitate easy alignment of grains, ensuring optimal imaging conditions for capturing images using either the one or more imaging devices 104 or a user-operated device 128. Further, the grooved plate 103a may function independently of motors 105 and 136, albeit requiring manual alignment of grains within the grooves. The motor 136 may be configured to enable vibration of the grooved plate 103a. Specifically, the motors 105 may be configured to enable oscillation and the motor 136 may be configured to enable vibration of the grooved plate 103a to advantageously facilitate even distribution of the grain sample onto the grooved plate 103a.
In some aspects of the present disclosure, the dispenser 101 may be coupled to the at least one motor of the one or more motors 105. The dispenser 101 may be vibrated. Specifically, the dispenser 101 may be vibrated by way of the at least one motor of the one or more motors 105 for even distribution of the grain sample on the grooved plate 103a.
In some aspects of the present disclosure, the grain sample may be distributed manually over the grooved plat 103a.
In some aspects of the present disclosure, the dispenser 101 may be adapted to provide motion by way of the first motor 105a to the grooved plate 103a to achieve an even distribution of the grain sample on the grooved plate 103a. In some aspects of the present disclosure, the grooved plate 103a may be detachably coupled to the dispenser 101. The grooved plate 103a may have pre-defined dimensions and pre-defined grooves. Specifically, the pre-defined dimensions and the pre-defined grooves of the grooved plate 103a may be designed depending on the type of Basmati rice grain to be analyzed. As illustrated, the pre-defined dimensions and the pre-defined grooves of the grooved plate 103a are designed for basmati rice. Specifically, when the grain sample is basmati rice, the grooved plate 103a may have a pre-defined number of grooves that may be in a range of 80 to 120, distributed between rows and columns forming a grid such that the grain sample (i.e., the basmati rice) dispensed in the grooved plate 103a gets aligned in the pre-defined number of grooves. In some aspects of the present disclosure, to align the grain sample (i.e., the basmati rice) in the grooved plate 103a, the grooved plate 103a may be moved back and forth by way of the second motor 105b and a vibratory motor 136 at a pre-defined angle. In other words, the grooved plate 103a may be oscillated by way of the second motor 105b and the vibratory motor 136 to ensure that the grain sample (i.e., the basmati rice) spread uniformly in the grid of the grooved plate 103a.
The one or more imaging devices 104 may be configured to capture (i) one or more low magnification images of the grooved plate 103a and/or (ii) one or more high magnification images of individual grain.
In some aspects of the present disclosure, the one or more imaging devices 104 may include an imaging sensor with one or more lens 108, a first interface (not shown), a first memory (not shown), and a first communication interface (not shown). The one or more imaging devices 104 may be configured to record a video/image. Examples of the one or more imaging devices 104 may include, but are not limited to, a camera, a video recorder, and the like. Aspects of the present disclosure are intended to include or otherwise cover any type of the imaging apparatus, without deviating from the scope of the present disclosure. The imaging sensor with one or more lens 108 (hereinafter referred to and designated as “the lens 108”) may be adapted to provide a high-magnification output that may resolve the features down to 1 micrometer per pixel, and hence, capture any kind of adulteration, especially intra grain adulteration, which is extremely difficult to detect at low-magnifications. Specifically, the imaging sensor with one or more lens 108 may be adapted to provide an optical resolution ranging from 1 – 125 µm per pixel, to capture the images of the grain sample (e.g., the basmati rice). Further, the high-magnification images may serve as excellent training data for the algorithms due to the richness of information available (each pixel is resolved to 1 micrometer). Thus, the prediction accuracy is very high, and therefore, adulteration can be detected with very high accuracy as well. Furthermore, with the high-magnification images, a user can customize the processing in the ML model to achieve a trade-off between prediction time and accuracy. For example, a user can take a 48 MP (Mega Pixel) image and morph the image down to 0.1 MP using the algorithm to reduce the training and testing time while not compromising with the accuracy. Advantageously, the system 100 facilitates creation of a dataset of the high-magnification images that are continuously uploaded to the information processing apparatus 118 and/or a cloud server. The lens 108 may include an optical complex and an extension piece. In some aspects of the present disclosure, the optical complex may be divided into three sections to obtain a parfocal and par center zoom images that can enable effective image processing of the grain sample. Further, the sections of the optical complex may include a fixed focus F-lens group, adapted to deliver sharp and clear images with an accurate color reproduction. Further, the optical complex may include a moveable Z-lens, adapted to magnifying the images. Furthermore, the optical complex may include a compensating lens, adapted to fine adjusting of the depth of field, which keeps the image in focus at different levels of zoom. In some aspects of the present disclosure, the one or more imaging devices 104 may be configured to capture one or more images of the grain sample by way of the imaging sensor with the lens 108, after the adjustment of calibration marks 134. Further, to capture images at various magnifications, the one or more imaging devices 104 may be employed at both the top and bottom of the grains. The one or more imaging devices 104 may be configured to capture images of the multiple grains sample simultaneously (low magnification images) using the user device 128 from one end and/or a single grain sample individually (high magnification images) from the other end. Further, the corresponding images are wirelessly transferred and processed by way of information processing apparatus 118.
In some aspects of the present disclosure, the plurality of illuminators 106 may be adapted to illuminate the grooved plate 103a. Thus, the plurality of illuminators 106 may advantageously facilitate the one or more imaging devices 104 to capture clearer one or more low magnification images, and one or more high magnification images. In some aspects of the present disclosure, the plurality of illuminators 106a and 106b may be disposed on each side of the grooved plate 103a and may be adapted to illuminate the grain sample. Examples of the plurality of illuminators 106 may include, but not limited to, a flashlight, a Light emitting diode (LED), an electric bulb, a fluorescent tube, a backlight, and the like. Aspects of the present disclosure are intended to include or otherwise cover any type of light source including known, related art, and/or later developed light sources, without deviating from the scope of the present disclosure. In some aspects of the present disclosure, the illuminators 106 may be operated by an automatic actuator (not shown) or manual actuator (not shown) or a combination thereof. Examples of automatic actuators may include, but are not limited to, a mobile based operating system, voice assistant, motion sensor, timer system, smart plug system, and the like. Aspects of the present disclosure are intended to include or otherwise cover any type of automatic actuator including known, related art, and/or later developed the automatic actuators, without deviating from the scope of the present disclosure. Examples of manual actuator may include but are not limited to a light switch, toggle switch, dimmer switch, pull chain, foot switch, key switch, push button, and the alike. Aspects of the present disclosure are intended to include or otherwise cover any type of manual actuator including known, related art, and/or later developed the manual actuator, without deviating from the scope of the present disclosure.
The processing circuitry 120 may be coupled to the apparatus 102. The processing circuitry 120 may be configured to pre-process the one or more low magnification images to generate one or more pre-processed images. Specifically, to pre-process the one or more low magnification images, the processing circuitry 120 may be configured to (i) convert the image into a greyscale image, (ii) convert the greyscale media into a binary image by way of a thresholding technique to identify the grooved plate 103a in the binary image, and (iii) extract one or more corners of the grooved plate 103a by way of edge detection from the binary image.
The processing circuitry 120 may be further configured to align the grooved plate 103a in the one or more pre-processed images by way of an image warping technique to extract one or more images of the individual grain by way of a classifier model.
In some aspects of the present disclosure, the processing circuitry 120 may be configured to implement the classifier model such that to train the classifier model, the processing circuitry 120 may be configured to (i) receive one or more high magnification images of the individual grain identified as specific species of the grains, (ii) pre-process the one or more high magnification images to generate a set of pre-processed images, and (iii) train the classifier model by way of the set of pre-processed images, wherein the classifier model is optimized by (a) scheduling a learning rate of the classifier model using a decay function and (b) applying model fitting to the classifier model by way of early stops and checkpoint callbacks.
The processing circuitry 120 may be further configured to pre-process the extracted one or more images of the individual rice grain. The processing circuitry 120 may be further configured to determine a set of physical features associated with the individual rice grain from the extracted one or more images of the individual rice grain, wherein each of the individual rice grains are identified as a basmati rice grain when (a) a length of the individual rice grain is greater than or equal to 6.61 mm, (b) a width of the individual rice grain is less than or equal to 2 mm, (c) an aspect ratio of the individual rice grain is greater than or equal to 3.5 mm. The processing circuitry 120 may be further configured to generate a report based on the identification of the individual rice grain as the basmati rice grain. The processing circuitry 120 may be further configured to facilitate to transmit the generated report to the user device 128.
In some aspects of the present disclosure, the user device 128 may be configured to receive one or more results of one or more parameters of the grain sample. The user device 128 may be configured to receive a representation of the state of the user from the information processing apparatus 118, which may be in the form of at least one of, a report, a pictorial representation, a graph, a text, a voice output, and the like. Aspects of the present disclosure are intended to include and/or otherwise cover any type of representation of the state of the user including known and/or related, or later developed representations.
In some embodiments of the present disclosure, the generated report may include number of adulterated basmati rice grains, number of unadulterated basmati rice grains, average length of the basmati rice grains, average width of the basmati rice grains, length of the basmati rice grains, width of the basmati rice grains, number of chalky rice grains, number of broken rice grains, and number of discoloured rice grains.
In some aspects of the present disclosure, the calibration marks 134 may be disposed on top and bottom faces of the grooved plate 103a. The calibration marks 134 may enable calibration of the one or more imaging device 104 with respect to the grooved plate 103a. In some aspects of the present disclosure, the calibration marks 134 may be adapted to provide essential information to increase the accuracy of the dimensions and quality of the image. Further, the calibration marks 134 may include, but not limited to, a reference colors of black (RGB 0,0,0), white (RGB 255,255,255), and mid-tone (RGB 128,128,128) for color temperature adjustments, red, green, and blue color references with known hex values for further color correction, a reference length for pixel/mm calibration, and square markings on the plate's four corners to facilitate distortion compensation for the reference length, reference width, reference height, and the like. Aspects of the present disclosure are intended to include or otherwise cover any type of reference without deviating from the scope of the present disclosure.
The user device holder 129 may be disposed on a top side of the apparatus 102. The user device holder 129 may be adapted to hold the user device 128. The user device holder 129 may be made up of a material such as, but not limited to, plastic, metal, and the like. Aspects of the present disclosure are intended to include and/or otherwise cover any type of the material for the user device holder 129, without deviating from the scope of the present disclosure.
In some aspects of the present disclosure, the first interface may be adapted to display the captured images and adjust the image reference. In some aspects of the present disclosure, the first interface may include an input interface (not shown) for receiving inputs from the user. Examples of the input interface of the first interface may include, but are not limited to, a touch interface, a mouse, a keyboard, a motion recognition unit, a gesture recognition unit, a voice recognition unit, or the like. Aspects of the present disclosure are intended to include or otherwise cover any type of the input interface including known, related art, and/or later developed technologies. The first interface may include an output interface (not shown) for displaying (or presenting) an output to the user. Examples of the output interface of the first interface may include, but are not limited to, a digital display, an analog display, a touch screen display, a graphical user interface, a website, a webpage, a keyboard, a mouse, a light pen, an appearance of a desktop, and/or illuminated characters. Aspects of the present disclosure are intended to include and/or otherwise cover any type of the output interface including known and/or related, or later developed technologies.
In some aspects of the present disclosure, the first memory may be configured to store the logic, instructions, circuitry, interfaces and/or codes and data associated with the one or more imaging devices 104. The first memory may be configured to save the images captured by the one or more imaging devices 104. Examples of the first memory may include but are not limited to, Read-Only Memory (ROM), Random-Access Memory (RAM), flash memory, a removable storage drive, a hard disk drive (HDD), a solid-state memory, magnetic storage drive, a Programmable Read Only Memory (PROM), an Erasable PROM (EPROM), and/or an Electrically EPROM (EEPROM). Aspects of the present disclosure are intended to include or otherwise cover any type of first memory 106 including known, related art, and/or later developed memories.
In some aspects of the present disclosure, the first communication interface may be configured to enable the one or more imaging devices 104 to communicate with other parts of the system 100. Examples of the first communication interface may include but are not limited to, a modem, a network interface such as an Ethernet card, a communication port, and/or a Personal Computer Memory Card International Association (PCMCIA) slot and card, an antenna, a radio frequency (RF) transceiver, one or more amplifiers, a tuner, one or more oscillators, a digital signal processor, a coder-decoder (CODEC) chipset, a subscriber identity module (SIM) card, and a local buffer circuit. It will be apparent to a person of ordinary skill in the art that the first communication interface may include any device and/or apparatus capable of providing wireless or wired communications between the other parts of the system 100.
FIG. 1C illustrates a perspective view of the grooved plate setup 103 of the system 100 of FIG. 1A, in accordance with an aspect of the present disclosure. The grooved plate setup 103 may include the grooved plate 103a as discussed above. Further, the grooved plate setup 103 may include a retractable backdrop 130, a photodiode 132, and the calibration marks 134. The grooved plate 103a may be configured to be vibrated and oscillated by way of the second motor 105b and the vibratory motor 136 in a pre-defined angle for distributing the grain sample across the grid.
In some aspects of the present disclosure, the second motor 105b and the vibratory motor 136 may be adapted to vibrate and oscillate the grooved plate 103a back and forth. Examples of the motors 105 may include, but not limited to, AC Servo Motor, Stepper Servo Motor, Brush DC Servo Motor, Permanent Magnet Synchronous Servo Motor, and Brushless DC Servo Motor. Aspects of the present disclosure are intended to include or otherwise cover any type of the motors, including known, related art, and/or later developed technologies.
The retractable backdrop 130 may be adapted to cover the grooved plate 103a when the retractable backdrop 130 is in a closed configuration. In some aspects of the present disclosure, the retractable backdrop 130 may be moved between the closed and open configurations by way of the third motor 105c motor. In some other aspects of the present disclosure, the retractable backdrop 130 may be moved between the closed and open configurations manually. The photodiode 132 may be adapted to facilitate in activation and/or deactivation of the motors 105 such that the motors 105 oscillating the grooved plate 103a are activated and/or deactivated based on a signal generated by the photodiode 132 corresponding to the optimal light intensity required for image acquisition. The calibration marks 134 may be adapted to facilitate calibrating the RGB color intensity and the dimensions of the grooved plate 103a for referencing the one or more imaging devices 104, the illuminators 106, and the user device 128.
In some aspects of the present disclosure, the grooved plate 130a may exhibit a dual-tone composition such that the central region may be of a single dark color, preferably black, while the surrounding area is of a contrasting light color, such as white. The dual-tome composition may enhance the detection of the central region. In some aspects of the present disclosure, the central region of the grooved plate 103a may be transparent, which further may enable imaging of grains from both the upper and lower sides.
For example, the system 100 may be configured to capture one or more low magnification images of the grooved plate 103a and one or more high magnification images of individual rice grain by way of the one and more imaging devices 104. Further, the system 100 by way of the processing circuitry 120 is configured to pre-process the one or more low magnification images to generate one or more pre-processed images, and align the grooved plate 103a in the one or more pre-processed images by way of an image warping technique to extract one or more images of the individual rice grain by way of a classifier model. The system 100 by way of the processing circuitry 120 may pre-process the extracted one or more images of the individual grain, and determine a set of physical features associated with the individual grain from the extracted one or more images of the individual grain, such that each of the individual grain may be identified as the specific species of the grain. In some aspect of the present disclosure, the system 100 by way of the processing circuitry 120 pre-process the extracted one or more images of the individual rice grain, and determine a set of physical features associated with the individual rice grain from the extracted one or more images of the individual rice grain, wherein each of the individual rice grains are identified as a basmati rice grain when (a) a length of the individual rice grain is greater than or equal to 6.61 mm, (b) a width of the individual rice grain is less than or equal to 2 mm, (c) an aspect ratio of the individual rice grain is greater than or equal to 3.5 mm. Further, the system 100 by way of the processing circuitry 120 generate a report based on the identification of the individual rice grain. For example, the generated report may include number of adulterated basmati rice grains, number of unadulterated basmati rice grains, average length of the basmati rice grains, average width of the basmati rice grains, length of the basmati rice grains, width of the basmati rice grains, number of chalky rice grains, number of broken rice grains, and number of discoloured rice grains.
FIG. 1D illustrates a block diagram of an information processing apparatus 118 of the system 100 of FIG. 1A, in accordance with an aspect of the present disclosure. The information processing apparatus 118 may include the processing circuitry 120, the database 124, a network interface 300, and an input-output (I/O) interface 302 communicatively coupled to one another by way of a first communication bus 304. The processing circuitry 120 may include a data extraction engine 306, a data collection engine 308, a training engine 310, a processing engine 312, and a fine-tuning engine 314. The data extraction engine 306, the data collection engine 308, the training engine 310, the processing engine 312 and the fine-tuning engine 314, may be coupled to each other by way of a second communication bus 316.
The data extraction engine 306 may be configured to extract a first set of parameters from predefined data. The first set of parameters may include but are not limited to primary features such as the length of the grain, a width of the grain, shape, texture, color, color gradients, and secondary features such as stripped, chalky, green, broken, discolored, and the like. Aspects of the present disclosure are intended to include or otherwise cover any type of physical feature of the grain, without deviating from the scope of the present disclosure.
The data collection engine 308 may be configured to collect one or more images captured by the one or more imaging devices 104. In some aspects of the present disclosure, the data collection engine 308 may be configured to store the collected images. In some aspects of the present disclosure, the data collection engine 308 may be configured to transmit the collected images to the training engine 310 in order to train the classifier model.
The training engine 310 may be configured to train the classifier model by employing the supervised and/or semi-supervised learning technique. The training engine 310 may be configured to use supervised or semi-supervised learning techniques to divide multiple training images from a labeled training dataset (typically representing grain sample features) into overlapping parameters of the grain sample. The training may involve the construction of a dataset through image capturing and annotation, training the model with natural images, and subsequently utilizing the classifier model.
The processing engine 312 may be configured to shuffle the parts of each training image and may determine a spatial relationship, contextual information, and an intrinsic structure between each part of each training image using one or more supervised or semi-supervised learning techniques. Further, the processing engine 312 may be configured to process the one or more input data and the one or more training datasets received by the training engine 310 to generate one or more processed output. Further, the processing engine may be configured to transmit the processed data for fine tuning.
The fine-tuning engine 314 may be configured to enhance the quality of image for the estimation of the parameters.
The database 124 may include a data extraction repository 320, a data collection repository 322, a training data repository 324, and a processed data repository 326.
The data extraction repository 320 may be configured to store the extracted first set of parameters. The data collection repository 322 may be configured to store the collected data of the captured images. The training data repository 324 may be configured to store the training data used for model training by training engine 310. The processed data repository 326 may be configured to store the processed data from the data processing engine 312.
The network interface 300 may include suitable logic, circuitry, and interfaces that may be configured to establish and enable a communication between the apparatus 102 and the information processing apparatus 118 via the communication network. The network interface 300 may be implemented by use of various known technologies to support wired or wireless communication of the information processing apparatus 118 with the communication network 138 (see Fig. 1A). The network interface 300 may include, but is not limited to, an antenna, a radio frequency (RF) transceiver, one or more amplifiers, a tuner, one or more oscillators, a digital signal processor, a coder-decoder (CODEC) chipset, a subscriber identity module (SIM) card, and a local buffer circuit. Aspects of the present disclosure are intended to include or otherwise cover any type of network interface, without deviating from the scope of the present disclosure.
The I/O interface 302 may include suitable logic, circuitry, interfaces, and/or code that may be configured to receive inputs (e.g., orders) and transmit outputs via a plurality of data ports in the information processing apparatus 118. The I/O interface 302 may include various input and output data ports for different I/O devices. Examples of such I/O devices may include, but are not limited to, a touch screen, a keyboard, a mouse, a joystick, a projector audio output, a microphone, an image-capture device, a liquid crystal display (LCD) screen and/or a speaker. Aspects of the present disclosure are intended to include or otherwise cover any type of I/O interface, without deviating from the scope of the present disclosure.
FIG. 2 illustrates a flow chart of a method 200 for detecting inter and intra adulteration in the grain sample, in accordance with an exemplary aspect of the present disclosure. The method 200 may be completed in two stages (i.e., a stage one and a stage two). The stage one may include steps 202 to 210 and the stage two may include steps 212 to 218. In some aspects of the present disclosure, the stage one may skip directly to the stage two. The method may include the following steps for detecting inter and intra adulteration in the grain sample: -
At step 202, the system 100, by way of the imaging apparatus 104, may capture one or more images of the grain sample. The imaging apparatus 104 may be arranged to capture the images of multiple grains at a time (i.e., low magnification images containing one or more images of the grain disposed over the transparent grooved plate 103) and/or single grain at a time (i.e., high magnification images) from the other end. The imaging apparatus 104 may be indexed and cropped to focus on specific regions of interest of the grain sample. Further, the captured images may be transmitted to the information processing apparatus 118. Specifically, the system 100, by way of the one or more imaging devices 104 of the apparatus 102 may be configured to capture one or more low magnification images of the grooved plate 103a.
At step 204, the system 100, by way of the processing circuitry 120 , may perform the pre-processing by way of the algorithm to generate one or more pre-processes images. The algorithm may include, but not limited to, You Only Look Once (YOLO), Single shot multi-box detector (SSD), RetinaNet, CenterNet, EfficientDet, YOLOv8, Convolutional Neural Networks (CNNs), AlexNet, Visual Geometry Group (VGG) networks, GoogLeNet (Inception), ResNet (Residual Networks), DenseNet, MobileNet, EfficientNet, Inception, ResNet and alike. Aspects of the present disclosure are intended to include or otherwise cover any type of the algorithm including known, related art, and/or later developed algorithm, without deviating from the scope of the present disclosure. The image processing may include conversion of the colored image to greyscale. Further, converting greyscale to a binary conversion (i.e., providing a threshold value for identifying a grid tray corner). Furthermore, the edge detection and extraction of the grid tray corner.
At step 206, the system 100 may be configured to align the grooved plate 103a in the one or more pre-processed images. Specifically, the system 100, by way of the processing circuitry 120, may be configured to align grooved plate 103a in the one or more pre-processed images. The processing circuitry 120 may align the grooved plate 103a by way of an image warping technique to extract one or more images of individual rice grain by way of a classifier model.
At step 208, the system 100, by way of the processing circuitry 120, may perform pre-processing of the extracted one or more images of the individual grain
At step 212, the system 100 may be configured to determine a set of physical features associated with the individual grain from the extracted one or more images of the individual species of the grain. In some aspects of the present disclosure, the system 100, by way of the processing circuitry 120, may be configured to determine the set of physical features associated with the individual specific species of the grain from the extracted one or more images of the grains.
At step 214, the system 100, by way of the processing circuitry 120, may perform pre-processing of the data obtained by analyzing the physical.
At step 216, the system 100, by way of the processing circuitry 120, may perform training of a classifier model via the set of pre-processed images wherein the classifier model is optimized by (a) scheduling a learning rate of the classifier model using a decay function and (b) applying model fitting to the classifier model by way of early stops and checkpoint callbacks.
At step 218, the system 100, by way of the processing circuitry 120, may be configured to generate the report based on the identification of the individual grain. In some aspects of the present disclosure, the system 100, by way of the processing circuitry 120, may be configured to generate the report based on the identification of the individual grain are identified as specific species of the grain. In some aspects of the present disclosure, the generated report may include number of adulterated grains, number of unadulterated grains, average length of the grains, average width of the grains, length of the grains, width of the grains, number of chalky grains, number of broken grains, and number of discoloured grains.
At step 220, the system 100, may perform transmitting the generated report to the user device 128.
For example, in some aspects of the present disclosure, the method may include capturing one or more low-magnification images of the grooved plate 103a. Specifically, the system 100, by way of the one or more imaging devices 104 of the apparatus 102 may be configured to capture one or more low magnification images of the grooved plate 103a. Further, the method may include capturing one or more high magnification images of individual rice grain. Specifically, the system 100, by way of the one or more imaging devices 104 may be configured to capture one or more low magnification images of the grooved plate 103a. Further, the method may include pre-processing of the one or more low magnification images to generate one or more pre-processed images. Specifically, the system 100, by way of the processing circuitry 120 that may be coupled to the apparatus 102, may be configured to pre-process the one or more low magnification images to generate one or more pre-processed images. Furthermore, the method includes aligning the grooved plate 103a in the one or more pre-processed images. Specifically, the system 100, by way of the processing circuitry 120, may be configured to align grooved plate 103a in the one or more pre-processed images. The processing circuitry 120 may align the grooved plate 103a by way of an image warping technique to extract one or more images of individual rice grain by way of a classifier model. Furthermore, the method may include pre-processing the extracted one or more images of the individual rice grain. Specifically, the system 100, by way of the processing circuitry 120, may be configured to pre-process the extracted one or more images of the individual rice grain. Furthermore, the method may include determining a set of physical features associated with the individual rice grain from the extracted one or more images of the individual rice grain. Specifically, the system 100, by way of the processing circuitry 120, may be configured to determine the set of physical features associated with the individual rice grain from the extracted one or more images of the individual rice grain. Each of the individual rice grains may be identified as the basmati rice grain when (a) a length of the individual rice grain is greater than or equal to 6.61 mm, (b) a width of the individual rice grain is less than or equal to 2 mm, (c) an aspect ratio of the individual rice grain is greater than or equal to 3.5 mm. Furthermore, the method may include generating the report based on the identification of the individual rice grain as the basmati rice grain. Specifically, the system 100, by way of the processing circuitry 120, may be configured to generate the report based on the identification of the individual rice grain as the basmati rice grain. Furthermore, the method may include transmitting the generated report to a user device 128. The generated report may include number of adulterated basmati rice grains, number of unadulterated basmati rice grains, average length of the basmati rice grains, average width of the basmati rice grains, length of the basmati rice grains, width of the basmati rice grains, number of chalky basmati rice grains, number of broken basmati rice grains, and number of discoloured basmati rice grains.
FIG. 3A and 3B illustrate a flow chart and a processed image, respectively for determination of the inter and intra adulteration in a rice grain sample, in accordance with an exemplary aspect of the present disclosure. As illustrated in FIG. 3A, firstly, the rice grain samples are distributed on the grooved plate. Further, the data construction is performed by image capturing of the rice grain samples distributed on the grooved plate by way of a smart phone. Further, in the data construction process, image annotation of the captured images of the rice grain samples distributed on the grooved plate by way of the Roboflow is performed. Further, as illustrated in FIG. 3B, the YoloV8 model is trained by providing the weight copy from a model pre-trained with natural images. Further, annotated image data from the data construction process is provided to a YoloV8 model. Further, as illustrated in FIG. 3A, testing is performed by employing the YoloV8 model to generate predictions related to the physical parameters of the rice grain sample (example length of a rice grain) distributed on the grooved plate using a test set. Further, as illustrated in FIG. 3B, intra adulteration of the rice grain sample is depicted in which different rice grains of the rice grain sample are classified into basmati and non-basmati rice grains, as well as chalky and non-chalky rice grains.
The foregoing discussion of the present disclosure has been presented for purposes of illustration and description. It is not intended to limit the present disclosure to the form or forms disclosed herein. In the foregoing detailed description, for example, various features of the present disclosure are grouped together in one or more aspects, configurations, or aspects for the purpose of streamlining the disclosure. The features of the aspects, configurations, or aspects may be combined in alternate aspects, configurations, or aspects other than those discussed above. This method of disclosure is not to be interpreted as reflecting an intention. The present disclosure requires more features than are expressly recited in each aspect. Rather, as the following aspects reflect, inventive aspects lie in less than all features of a single foregoing disclosed aspect, configuration, or aspect. Thus, the following aspects are hereby incorporated into this detailed description, with each an aspect standing on its own as a separate aspect of the present disclosure.
Although the description of the present disclosure has included a description of one or more aspects, configurations, or aspects and certain variations and modifications, other variations, combinations, and modifications are within the scope of the present disclosure, e.g., as may be within the skill and knowledge of those in the art, after understanding the present disclosure. It is intended to obtain the rights which include alternative aspects, configurations, or aspects to the extent permitted, including alternate, interchangeable and/or equivalent structures, functions, ranges, or steps to those disclosed, whether or not such alternate, interchangeable and/or equivalent structures, functions, ranges, or steps are disclosed herein, and without intending to publicly dedicate any patentable subject matter.
As one skilled in the art will appreciate, the system 100 includes a number of functional blocks in the form of a number of units and/or engines. The functionality of each unit and/or engine goes beyond merely finding one or more computer algorithms to carry out one or more procedures and/or methods in the form of a predefined sequential manner, rather each engine explores adding up and/or obtaining one or more objectives contributing to an overall functionality of the system 100. Each unit and/or engine may not be limited to an algorithmic and/or coded form but rather may be implemented by way of one or more hardware elements operating together to achieve one or more objectives contributing to the overall functionality of the system 100. Further, as will be readily apparent to those skilled in the art, all the steps, methods and/or procedures of system 100 are generic and procedural in nature and are not specific and sequential.
Certain terms are used throughout the following description and aspects to refer to particular features or components. As one skilled in the art will appreciate, different people may refer to the same feature or component by different names. This document does not intend to distinguish between components or features that differ in name but not structure or function. While various aspects of the present disclosure have been illustrated and described, it will be clear that the present disclosure is not limited to these aspects only. Numerous modifications, changes, variations, substitutions, and equivalents will be apparent to those skilled in the art, without departing from the spirit and scope of the present disclosure.
,CLAIMS:1. A system (100) to detect inter and intra adulteration in a basmati rice grain sample placed in a grooved plate (103a), the system (100) comprising:
an apparatus (102) comprising one or more imaging devices (104) configured to capture (i) one or more low magnification images of the grooved plate (103a) and/or (ii) one or more high magnification images of individual rice grain; and
processing circuitry (120) that is coupled to the apparatus (102), and configured to (i) pre-process the one or more low magnification images to generate one or more pre-processed images, (ii) align the grooved plate (103a) in the one or more pre-processed images by way of an image warping technique to extract one or more images of the individual rice grain by way of a classifier model, (iii) pre-process the extracted one or more images of the individual rice grain, (iv) determine a set of physical features associated with the individual rice grain from the extracted one or more images of the individual rice grain, wherein each of the individual grain are identified as specific species of the grain, and (v) generate a report based on identification of the individual grain as the specific species of the basmati rice grain.

2. The system (100) as claimed in claim 1, wherein the one or more imaging devices (104) comprising a plurality of lenses (108) such that the plurality of lenses (108) is adapted to provide an optical resolution in a range of 1 micrometer (µm) per pixel to 125 micrometer (µm) per pixel.

3. The system (100) as claimed in claim 1, wherein to pre-process the one or more low magnification images, the processing circuitry (120) is configured to convert the image into a greyscale image, convert greyscale media into a binary image by way of a thresholding technique to identify the grooved plate (103a) in the binary image, and extract one or more corners of the grooved plate (103a) by way of edge detection from the binary image.

4. The system (100) as claimed in claim 1, wherein the apparatus (102) further comprising a user device (128) such that the processing circuity (120) is configured to transmit the generated report to the user device (128).

5. The system (100) as claimed in claim 1, wherein the apparatus (102) comprising one or more motors (105a-105c) coupled to the grooved plate (103a) such that the one or more motors (105a-105c) is configured to enable vibration, and back and forth oscillation of the grooved plate (103a) for even distribution of the rice grain sample onto the grooved plate (103a).

6. The system (100) as claimed in claim 1, wherein the apparatus (102) comprising the grooved plate (103a) exhibits a dual-tone composition: a central region, housing the grids, is of a single dark color, and the surrounding area is of a contrasting light color.

7. The system (100) as claimed in claim 1, wherein the apparatus (102) comprising a dispenser (101) coupled to at least one motor of the one or more motors (105a-105c), wherein the dispenser (101) is vibrated by way of the at least one motor of the one or more motors (105a-105c) for even distribution of the rice grain sample onto the grooved plate (103a).

8. The system (100) as claimed in claim 1, wherein the apparatus (102) comprising a plurality of illuminators (106) adapted to illuminate the grooved plate (103a).

9. The system (100) as claimed in claim 1, wherein the apparatus (102) comprising a plurality of calibration marks (134) disposed on top and bottom faces of the grooved plate (103a) such that the plurality of calibration marks (134) enables calibration of the one or more imaging devices (104) with respect to the grooved plate (103a).

10. The system (100) as claimed in claim 1, wherein the processing circuitry (120) implements the classifier model such that to train the classifier model, the processing circuitry (120) is configured to (i) receive one or more high magnification images of the individual rice grain identified as the basmati rice grains, (ii) pre-process the one or more high magnification images to generate a set of pre-processed images, (iii) train the classifier model by way of the set of pre-processed images, wherein the classifier model is optimized by (a) scheduling a learning rate of the classifier model using a decay function and (b) applying model fitting to the classifier model by way of early stops and checkpoint callbacks.

11. A method (200) for detecting an inter and intra adulteration in a rice grain sample placed in a grooved plate (103a), the method (200) comprising:
capturing (202), by way of one or more imaging devices (104) of an apparatus (102), one or more low magnification images of the grooved plate (103a);
pre-processing (204), by way of processing circuitry (120) coupled to the apparatus (102), the one or more low magnification images to generate one or more pre-processed images;
aligning (206), by way of the processing circuitry (120), the grooved plate (103a) in the one or more pre-processed images, wherein the processing circuitry (120) aligns the grooved plate (103a) by way of an image warping technique to extract one or more images of individual rice grain by way of a classifier model;
pre-processing (208), by way of the processing circuitry (120), the extracted one or more images of the individual rice grain; and
determining (210), by way of the processing circuitry (120), a set of physical features associated with the individual rice grain from the extracted one or more images of the individual rice grain, wherein each of the individual grain is identified as a Basmati rice grain.

12. The method (200) as claimed in claim 11, wherein the one or more imaging devices (104) comprising a plurality of lenses (108) such that the plurality of lenses (108) is adapted to provide an optical resolution in a range of 1 micrometer (µm) per pixel to 125 micrometer (µm) per pixel.

13. The method (200) as claimed in claim 11, wherein to pre-process the one or more low magnification images, the processing circuitry (120) is configured to convert the image into a greyscale image, convert the greyscale media into a binary image by way of a thresholding technique to identify the grooved plate (103a) in the binary image, and extract one or more corners of the grooved plate (103a) by way of edge detection from the binary image.

14. The method (200) as claimed in claim 11, further comprising:
capturing (212), by way of the one or more imaging devices (104), one or more high magnification images of individual basmati rice grain;
pre-processing (214), by way of the processing circuitry (120), the one or more high magnification images of individual grain to generate a set of pre-processed images; and
training (216), by way of the processing circuitry (120), the classifier model via the set of pre-processed images wherein the classifier model is optimized by (a) scheduling a learning rate of the classifier model using a decay function and (b) applying model fitting to the classifier model by way of early stops and checkpoint callbacks.
15. The method (200) as claimed in claim 11, further comprising generating (218), by way of the processing circuitry (120), a report based on the identification of the individual grain as the basmati rice grain.

16. The method (200) as claimed in claim 11, wherein upon generating the report, the method (200) further comprising transmitting (220) the generated report to a user device (128).