Description:
FIELD OF THE INVENTION

Embodiments of the invention in general relate to a method and system for Particle Size Distribution, PSD, and more particularly to an artificial intelligence-based tobacco particle measurement system.

BACKGROUND OF THE INVENTION

Particle Size Distribution, PSD, is one of the critical physical quality parameters measured for lamina (Final Product) in Green Leaf Tobacco Threshing Process. PSD is defined as the ratio of weight of different sizes of lamina particles (above 1’’, ½’’, 1/4’’, 1/8’’ etc.) present in the lamina (final product) sample to the total sample weight taken before lamina is packed in to cases.

Stem in Lamina, SIL, is defined as the ratio of weight of stem present in the lamina sample to the total sample weight taken. Objectionable Stem, OBJ, is defined as the ratio of stem with diameter > 3/32’’ present in the Lamina sample.

In any conventional measurement system, PSD is measured manually by collecting a lamina sample (e.g. 3 Kg ± 300 gm) from an exit of a lamina re-dryer as per customer approved procedure and sieved in a four tier sieve tester to separate different sizes of lamina particles to measure the percentage (%) of different particles in the sample and the sample is further tested in stem testing machine to measure stem content in the lamina sample involving partial destruction of the sample.

Reference is made to CN103743486B, teaching an automatic Grading System based on magnanimity tobacco leaf data and method, and it is a kind of system utilizing computer vision, graphical analysis, machine learning, the greatly technique algorithm of data retrieval and artificial intelligence to analyse tobacco leaf image, store, retrieve and automatically define the level. The technology of Mass Data Searching introduced in automatic tobacco leaf rating system, build corresponding database and efficient search engine, make the result of deciding grade and level more accurate. The system implemented is used to identify & grade different kinds of Unmanufactured Green Leaf tobacco. Images captured are compared against the existing green leaf tobacco images in the database and close match result is provided.

Reference is further made to IN201841046028 teaching a dimension measurement system, where the substrate is generally cylindrical in nature (wooden log) which is non-degradable during handling. Edge detection algorithm is used to detect the length and width of the substrate. However, the system has no mechanism for creation of monolayer of the substrate to prevent overlapping, cannot measure the weight & density of the substrate and further cannot differentiate density variation in the substrate.

The conventional measurement system is as per the CORESTA guidelines (Cooperation Centre for Scientific Research Relative to Tobacco) which is being followed across Green Leaf Tobacco Processing. However, the existing systems and measurement methods, have the following drawbacks –

(a) The testing is done at an interval of 30 minutes and time consuming (20 Min/Test) leading to delayed corrections in the process. The current measurement system is a lag indicator for process correction i.e. 50 minutes of processing has already been carried out by the time when the test results are known.
(b) The test involves partial degradation of the sample leading to loss of valuable lamina.
(c) The testing process is highly laborious due to the manual nature of activities such as sample collection, testing, computation of results and adding back good lamina into the process and the frequency of testing is also very high (once in 30 minutes).

Thus, there is a need for an advanced, faster and automated particle size measurement method and system for non-destructive measurement of particle size and stem content in lamina tobacco, said system based on Artificial Intelligence (AI) and Image Analytics (IA) in quality measurement of tobacco lamina.

SUMMARY OF THE INVENTION

The following presents a simplified summary of the invention in order to provide a basic understanding of some aspects of the invention. This summary is not an extensive overview of the present invention. It is not intended to identify the key/critical elements of the invention or to delineate the scope of the invention. Its sole purpose is to present some concept of the invention in a simplified form as a prelude to a more detailed description of the invention presented later.

An objective of present invention is to provide AI and image analytics based advanced, faster and automatic particle size measurement method and system for non-destructive measurement of particle size and stem content in lamina tobacco to address the aforementioned drawbacks of the prior art.

According to one aspect of the present invention, a real time, automatic, particle measurement system for a variety of agricultural products and confectionaries having an irregular shape and size is disclosed. The system comprises: a conveyor unit comprising a plurality of multi-speed counter direction conveyors, said conveyors being adapted to create a monolayer of the agricultural products and confectionaries sample; a camera vision system positioned in proximity to the conveyor unit, said camera vision system comprising a combination of at least one colour camera and at least one monochrome camera with Infra-Red backlight, the at least one colour camera being adapted to detect the particle size of the agricultural products and confectionaries sample, and the at least one monochrome camera being adapted to detect the particle density of the agricultural products and confectionaries sample; and an integration system comprising a PLC controller, an interface panel for display of results, and a data acquisition system for storage and reporting of data of the agricultural products and confectionaries sample.

According to another aspect of the present invention, a real time, automatic, particle measurement method for a variety of agricultural products and confectionaries having an irregular shape and size is disclosed, the method comprising the steps of: sampling of agricultural products and confectionaries sample from an input main line; feeding of the drawn agricultural products and confectionaries sample into a particle measurement system, the system comprising a conveyor unit comprising a plurality of multi-speed counter direction conveyors, a camera vision system positioned in proximity to the conveyor unit, said camera vision system comprising a combination of at least one colour camera and at least one monochrome camera with Infra-Red backlight, and an integration system comprising a PLC controller, an interface panel for display of results, and a data acquisition system for storage and reporting of data of the agricultural products and confectionaries sample; creating a monolayer of the agricultural products and confectionaries sample feed, by the plurality of multi-speed counter direction conveyors; detecting the particle size of the agricultural products and confectionaries sample, and detect the particle density of the agricultural products and confectionaries sample from the monolayer of the sample, by the camera vision system; and displaying and storage of data of the agricultural products and confectionaries sample.

Other aspects, advantages, and salient features of the invention will become apparent to those skilled in the art from the following detailed description, which, taken in conjunction with the annexed drawings, discloses exemplary embodiments of the invention.

BRIEF DESCRIPTION OF ACCOMPANYING DRAWINGS

The above and other aspects, features and advantages of the embodiments of the present disclosure will be more apparent in the following description taken in conjunction with the accompanying drawings, in which:

Figures 1 (a)-(d) illustrate Particle Size Distribution of different sizes of Lamina particles, Stem in Lamina and Objectionable Stem, of a lamina sample, in Green Leaf Tobacco Threshing Process, according to an embodiment of the present invention.

Figure 2 illustrates a real time, automatic, particle measurement system, for a variety of agricultural products and confectionaries having an irregular shape and size according to an embodiment of the present invention.

Figure 3 illustrates the image processing methodology implemented by a different combination of colour and monochrome cameras to extract the exact data from a monolayer product and IR backlight to detect the Stem in Lamina, according to an embodiment of the present invention.

Figure 4 illustrates a mechanism for creation of monolayer generation, achieved through the counter direction multi speed conveyors, according to an embodiment of the present invention.

Figure 5 illustrates detection of particle sizes and stem content in a lamina sample, by a combination of colour and monochrome cameras respectively, to extract the exact data from a monolayer product of the lamina sample, according to an embodiment of the present invention.

Figure 6 illustrates Particle Size measurement variation between conventional and the present AI based PSD measurement method, according to an embodiment of the present invention.

Figure 7 illustrates a flow diagram of the working of the artificial intelligence based tobacco particle measurement system according to an embodiment of the present invention.

Persons skilled in the art will appreciate that elements in the figures are illustrated for simplicity and clarity and may have not been drawn to scale. For example, the dimensions of some of the elements in the figure may be exaggerated relative to other elements to help to improve understanding of various exemplary embodiments of the present disclosure. Throughout the drawings, it should be noted that like reference numbers are used to depict the same or similar elements, features, and structures.

DETAILED DESCRIPTION

The following description with reference to the accompanying drawings is provided to assist in a comprehensive understanding of various embodiments of the present disclosure as defined by the claims and their equivalents. It includes various specific details to assist in that understanding but these are to be regarded as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the various embodiments described herein can be made without departing from the scope and spirit of the present disclosure. In addition, descriptions of well-known functions and constructions may be omitted for clarity and conciseness.

The terms and words used in the following description and claims are not limited to the bibliographical meanings, but, are merely used by the inventor to enable a clear and consistent understanding of the present disclosure. Accordingly, it should be apparent to those skilled in the art that the following description of various embodiments of the present disclosure is provided for illustration purpose only and not for the purpose of limiting the present disclosure as defined by the appended claims and their equivalents.

It is to be understood that the singular forms “a,” “an,” and “the” include plural referents unless the context clearly dictates otherwise. Thus, for example, reference to “a component surface” includes reference to one or more of such surfaces.

All terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which various embodiments belong. Further, the meaning of terms or words used in the specification and the claims should not be limited to the literal or commonly employed sense, but should be construed in accordance with the spirit of the disclosure to most properly describe the present disclosure.

The terminology used herein is for the purpose of describing particular various embodiments only and is not intended to be limiting of various embodiments. As used herein, the singular forms “a”, “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises” and/or “comprising” used herein specify the presence of stated features, integers, steps, operations, members, components, and/or groups thereof, but do not preclude the presence or addition of one or more other features, integers, steps, operations, members, components, and/or groups thereof. Also, Expressions such as “at least one of,” when preceding a list of elements, modify the entire list of elements and do not modify the individual elements of the list.

The present disclosure will now be described more fully with reference to the accompanying drawings, in which various embodiments of the present disclosure are shown. The present disclosure may, however, be embodied in many different forms and should not be construed as being limited to the various embodiments set forth herein, rather, these various embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the present disclosure. Furthermore, a detailed description of other parts will not be provided not to make the present disclosure unclear. Like reference numerals in the drawings refer to like elements throughout.

The subject invention lies in an advanced and automatic particle size measurement method and system for fast and non-destructive measurement of particle size and stem content in lamina tobacco, thereby minimizing manual intervention in the testing process.

In an embodiment, Artificial Intelligence (AI) with Image Analytics (IA) facilitates automatic and faster testing for PSD, with minimizing manual intervention thereby eliminating degradation of the sample during testing and improves the response time for process correction. Further, the method facilitates the capability to effectively measure Stem In Lamina (SIL) and Objectionable Stem (OBJ) in the Lamina sample.

In particular, Camera Vision (CV) Technology has been leveraged for implementation of the Particle Measurement System.

AI emphasizes the creation of intelligent machines that work and react like humans. Image analysis is the extraction of meaningful information from images; mainly from digital images by means of digital image processing techniques. The major techniques used in an embodiment are: Image Segmentation - the operation of partitioning an image into a collection of connected sets of pixels; and Image Analytics - the segmented image is used to calculate the area of the different size of the particles there by calculating the PSD.

In an exemplary implementation, advanced image processing techniques (Image Segmentation, Image Thresholding etc.) and image data is processed for measurement of lamina sizes, stem content and results are displayed on real time basis.

In an embodiment, AI based PSD and the corresponding measurement method facilitates tobacco particle measurement, where the substrate is irregular in shape and size (Threshed Tobacco Lamina Particles) which is easily degradable during handling. The complex and advanced colour and edge detection along with density variation detection using monochrome camera with IR backlight enables measurement of the pixel area of lamina and stem, auto density factor calculation of lamina and stem, detection and differentiation of lamina and stem in the testing sample having different physical and chemical properties, automatic calculation of weight of lamina and stem and auto calculation of Particle size Distribution (PSD) of threshed tobacco lamina sample. Density measurement has the capability to measure the area in pixel form, and converts into weight using auto density factor, and density variation detection identifies density variation in the substrate and performs calculation for segregated density wise sub groups.

In an embodiment, the AI based PSD method can measure the Particle Size Distribution and stem content of the threshed tobacco lamina during green leaf threshing process. It further detects lamina and segregates in to different size brackets (1’’, 1-1/2’’ etc) and detects stem content and measure the stem content in the testing sample.

In an embodiment, the system comprises a system for creation of monolayer, a camera vision system comprising different combination of colour and monochrome cameras to extract the exact data from the monolayer product and IR backlight is used to detect the Stem in Lamina, SIL, and an integration system including the like of PLC controller, interface panel for display of results, data acquisition system for storage and reporting of data. In an implementation, the system can efficiently handle agricultural product i.e. tobacco with varying physical properties like bulk density, moisture etc.

The system, as illustrated in Figure 2, comprises a hopper for uniform flow of the product without degradations, a feed vibrator for distribution of the product across the width of the conveyors, multi speed conveyors adapted to create a monolayer of the tobacco sample, a colour camera to detect the particle size of the tobacco sample and a mono chrome camera to detect the Stem content (Stem In Lamina, Objectionable Stem) in the tobacco sample.

In an embodiment, the system facilitates creation of monolayer through counter direction multi speed conveyors as shown in Figure 4. The three conveyors convey the product in opposite direction and modulation of speed was done from first conveyor to the last conveyor by carrying the speed at an incremental rate of 20-50% depending on the type of tobacco. The incremental speed down the flow on multi stage counter direction conveyors reduces the tobacco carpet and at the output of last conveyor each particle is separated against other, thereby monolayer is achieved for accurate measurement of the particle sizes of lamina and stem.

The camera vision system consists of two sets of cameras - colour camera for detection of particle sizes and monochrome camera with IR backlight for detection of stem content in the sample. The video output of the colour camera is processed through different filters (1’’ size filter, ½’’ size filter, ¼’’ size filter etc.) for detection of the particles and segregation of the same.

In an embodiment, the system is adapted to detect the tobacco present using images stored in a database for different kinds of tobacco. The raw image/video data of the camera vision system is processed to remove the background and only tobacco particles are detected automatically. The original data is converted to saturation image, wherein thresholding technique is used to detect the contours of each and every particle. The detected tobacco particle sizes are measured in terms of pixels and these pixels are displayed and stored instantaneously. 1-inch filter will only detect the particles which are greater than or equal to 1 inch and similar is the case for ½’’, ¼’’ etc. Overall calculation is carried out for PSD measurement and these values are displayed on real time. The following is the schematic representation of the filter and products:

The weight of the sample is directly captured from a weigh scale and stored in the data base and the Quality Ratio & Thru 1/4’’ Product is calculated.

As shown in Figures 5 (a)-(c), the monochrome camera with Infrared backlight is used for detection of stem content present in the lamina sample. The lamina and stem are differentiated in terms of density i.e. how closely the molecules are to each other. Lamina being less dense than stem it allows more IR light to transmit whereas stem being dense blocks the IR light. The variation in transmission of the IR light is used as reference for detection of stem by keeping lamina transmission value as threshold.

The threshold is arrived during the calibration process of the system and ensured that only stem is being detected from the sample. There are four filters created with the following features:
? 3/32 Inch Filter: It adds up pixels value of stem diameter greater than or equal to 3/32 inch and length 40mm
? 7 Mesh Filter: It adds up pixels value of stem diameter greater than 0.111 inch
? 12 Mesh Filter: It adds up pixels value of stem diameter greater than 0.066 inch
? PAN: It adds up pixels value of stem diameter less than 0.066 inch

The following is the schematic representation of the filter and products:

The essential parameters Stem in Lamina (SIL) & Objectionable Stem are calculated.

The threshold is being generated during the calibration process before testing of the sample and is fixed for a particular type of tobacco. The calibration process involves the following operations – (a) inspection of both camera and ensuring the lens are clean, (b) checking the Frames Per Second (FPS) of both the camera and adjusting the encode signal for accurate FPS as per the design, (c) checking the area of study for both the camera, (d) calibration of Colour Camera, and (e) calibration of Mono Chrome Camera.

The calibration of Colour Camera comprises the following steps - proper implementation of camera vision techniques i.e. segmentation and thresholding etc., proper capturing of all types of tobacco, elimination of interference of dust particles, checking the pixel calculation by placing known sample (Area know samples) and adjusting the height & focus of the camera accordingly.

The calibration of Mono Chrome Camera comprises the following steps - proper working of IR Back light at the bottom of the conveyor, setting the threshold values to ensure proper separation and identification of stem from the sample, checking the pixel calculation by placing known sample (Area know samples) and adjusting the height & focus of the camera accordingly.

The above calibration process is carried out for one category of tobacco and saved as recipes under the recipe management system. During particle size measurement the category of tobacco is chosen and the calibrated values are used while particle size measurement of the sample.

Therefore, the detection and differentiation of lamina and stem is done with the help predetermined threshold value for a particular category of tobacco during calibration process we are able to differentiate stem and lamina, thereby ensuring detection and differentiation of lamina and stem in the sample which have different physical and chemical properties. Automatic calculation of Weight of Lamina, Stem and Auto Calculation of PSD of threshed tobacco lamina sample are done as described above.

The integration system comprises a PLC Controller configured to control and operate the overall system as per predetermined sequence with high repeatability and reproducibility, servo motors adapted to vary speed of conveyors for creation of a monolayer, an encoder to trigger the cameras for capturing images / video with highest accuracy of frames per second and eliminating overlapping.

In an exemplary implementation, the PLC received information from connected sensors or input devices (i.e. cameras), processes the data & triggers outputs based on pre-programmed parameters. The PLC controls the operation of the all the sub processes like conveyors, power supply to cameras, speed of conveyors and signal from encoder etc.

The CV-X Controller for Camera Vision is an image processing unit and facilitates the measurement process. The controller has the capability to implement several features as following:

? Trend Edge Detection: This feature extracts a profile from the edges of a work piece and recognises the sections that show a large difference from the profile as burrs or flaws detection. In addition to circles and straight lines, ovals and profiles with complex shapes consisting of free curves are supported, based on edge information of up to 5000 points.
? Shading Correction: Cancels shading or uneven brightness occurring on the work piece surface to optimise images for inspection. Even if shading conditions change every time, this filter corrects images in real time to only extract required section.
? Noise Isolation: Eliminates or, in contrast, extracts noise having a specified area or smaller. This filter is effective when a rough background hinders image processing.
? Contrast Expansion: Expands the intensity distribution within the inspection region to increase the contrast of an image. This filter stabilises inspection when gradation necessary for image processing cannot be obtained.
? Blur: Blurs the inspection region to remove a significant amount of fine background patterns or noise. This filter offers a more stable inspection by intentionally blurring images to eliminate featured points that doesn’t need to be inspected.
? Subtraction: Compares the target with a preregistered master quality image to extract sections that differ. It is also possible to take individual differences in non-defective work pieces into account and adjust how much differences should be recognised as defective.
? Preserve Intensity: Corrects changes in image brightness due to light intensity fluctuation. This filter reduces variation in measured values caused by intensity fluctuation by correcting the brightness difference from the reference image at every capture.
? Measurement & Dimensions: These features are used for measurements techniques in image processing.
? Statistics of Image Processing: Up to 20,000 pieces of measurement data can be recorded with the controller alone. It is possible to easily check the value such as minimum, maximum, average, standard deviation, NG count. In addition to the trend graphs, a list of measured values and a histogram can be displayed. Also, by using the newly included function, Process Monitor (process capability index: Cpk), it is possible to analyse the inspection processes more statistically.

The incremental rotary encoder is a type of electromechanical device that converts the angular motion or position of a rotary shaft into analog or digital code that represents that motion or position. The use of incremental encoders is always required when using cameras vision system. The aim is to synchronise the path covered and the pixel size. Only in this way the image will be free of distortion and have the same imaging scale in transport direction and across the conveyor.

In an exemplary implementation, the testing includes the following procedure:

Step (a): Two 3 Kg samples are taken simultaneously at exit of lamina re-dryer to ensure no variations in the sample.

Step (b): One sample is fed in to the conventional system and the other in to AI based PSD measurement system

Step (c): The results are analysed and insights are generated for necessary fine tuning of the AI based PSD System.

The following are the critical improvements carried out for improving the performance of the AI based PSD Measurement System. It was noticed that Particle Size Distribution in the conventional system is dependent on the orientation of the particle during the sieving operation. This factor was incorporated into the AI based PSD system, by a teach back process where the segregated 1inch, ½ inch, ¼ inch, 1/8 inch from conventional system are fed to the AI based PSD system. Significant difference in 1’’, ½’’ and through ¼’’ results were observed for the AI based PSD system in comparison to the conventional system.

With the help of internal data analytics, the pixel area limits for each filter are calculated and best settings for filters are arrived, as shown in Figure 6. Figure 6 (a) illustrates the conventional sieve tester with different orientations of the particle (threshed tobacco) and the corresponding conventional method (CORESTA) has been shown in Figure 6 (b).

There is a difference in system measured weight and actual sample weight. This is majorly due to improper density factor calculation. In order to improve the weight measurement, the AI based PSD system is configured for auto weight capturing from the weigh scale directly, thereby enabling better density calculation and reducing the error of measurement.

Moreover, image overlapping and inaccurate identification of the stem, can cause inaccurate measurement of the PSD. In order to prevent this issue, FPS (Frames per second) calibration process has been incorporated in the PLC for calibration and recording as and when required. In order to measure the stem present in the sample accurately, different colours of stem are prestored in the AI based PSD system to enable better detection of the stem in the sample.

In embodiments as described above, the type of material, bulk density and quantity of the product defines the number of conveyors required for creation of monolayer. The current number of conveyors used in the exemplary implementation above is 3. The number of conveyors required for creation of monolayer is arrived at by carrying out several experimentations with all types of tobacco during the development stage. Basis on this experimentation the minimum number of conveyors required for creation of monolayer for a 3KG sample is 3 conveyors.

In other embodiments, particle size measurement of any irregular shaped agricultural and food products such as cashew, almonds, ground nuts, rice, wheat, potato chips, biscuits, confectionaries etc. can be performed. The system is flexible in nature and can be appropriately modified to capture the need i.e. what type of measurement. In case of almonds / cashew / rice / wheat: the system has the capability to detect and count broken grains i.e. broken almonds / rice / wheat etc. It further detects damaged grains in terms of colour. In case of potato chips/biscuits/confectionaries: the system is adapted to compare the dimensions of the product against standard dimensions. It also detects defectives like over fried potato chips, broken biscuits, confectionaries on the basis of colour detection and edge detection techniques. Therefore, complete working parameters and system parameters can be fine-tuned for the respective application without any need of other systems.

Some of the non-limiting advantages of tobacco particle measurement system are:

1. Implementation of Artificial Intelligence (AI) & Image Analytics (IA) in quality measurement of tobacco lamina.
2. Non-Destructive measurement of particle size and stem content in lamina tobacco and elimination of manual intervention in measurement process.
3. Faster measurement of PSD at processing line near Lamina Re-dryer exit.
4. Particle size measurement of any irregular shaped Agricultural and food products such as Cashew, Almonds, Ground nuts, Rice, wheat, Potato chips, biscuits, confectionaries etc.
5. Particle size measurement of any product which is brittle, low bulk density with irregular shape at optimum moisture range (9%-20%) can be measured.

Although an artificial intelligence based tobacco particle measurement system thereof has been described in language specific to structural features, it is to be understood that the embodiments disclosed in the above section are not necessarily limited to the specific methods or devices described herein. Rather, the specific features are disclosed as examples of implementations of artificial intelligence based tobacco particle measurement system.

Claims:
1. A real time, automatic, particle measurement system for a variety of agricultural products and confectionaries having an irregular shape and size, the system comprising:
a conveyor unit comprising a plurality of multi-speed counter direction conveyors, said conveyors being adapted to create a monolayer of the agricultural products and confectionaries sample;
a camera vision system positioned in proximity to the conveyor unit, said camera vision system comprising a combination of at least one colour camera and at least one monochrome camera with Infra-Red backlight, the at least one colour camera being adapted to detect the particle size of the agricultural products and confectionaries sample, and the at least one monochrome camera being adapted to detect the particle density of the agricultural products and confectionaries sample; and
an integration system comprising a PLC controller, an interface panel for display of results, and a data acquisition system for storage and reporting of data of the agricultural products and confectionaries sample.

2. The system as claimed in claim 1, further comprises:
a hopper for uniform flow of the agricultural products and confectionaries without degradations;
a feed vibrator for distribution of the agricultural products and confectionaries across the width of the plurality of conveyors of the conveyor unit.

3. The system as claimed in claim 2, wherein the plurality of conveyors of the conveyor unit is adapted to convey the agricultural products and confectionaries in opposite direction and the speed being modulated from first conveyor to the last conveyor by carrying the speed at an incremental rate of depending on the type of product, and the incremental speed down the flow on multi-stage counter direction conveyors reduces the facilitates separation of each particle against other, thereby creating a monolayer for particle size measurement.

4. The system as claimed in any one of claims 1-3, wherein the system further comprises a processing unit, said processing unit being configured to
convert an image/video captured by the camera vision system into a saturation image;
detect contours of each and every single particle of a tobacco sample or each and every single product of the agricultural products and confectionaries sample;
measure the detected particles in terms of pixels and store them.

5. The system as claimed in claim 1, wherein the system facilitates fast and non-destructive measurement of particle size and stem content in lamina tobacco.

6. The system as claimed in claim 5, wherein the at least one colour camera is adapted to detect the particle size of the tobacco sample and the at least one monochrome camera is adapted to detect the Stem content (Stem In Lamina, Objectionable Stem) in the tobacco sample and a video output of the colour camera is processed through different filters, like 1’’ size filter, ½’’ size filter, ¼’’ size filter, by the processing unit, for detection of the particles and segregation of the same.

7. The system as claimed in claim 1, wherein the PLC Controller is configured to control and operate the overall system as per predetermined sequence with high repeatability and reproducibility,
wherein the conveyor unit is operably coupled to servo motors adapted to vary speed of conveyors for creation of a monolayer, and
and the camera vision system is operably coupled to an encoder to trigger the at least one colour camera and the at least one monochrome camera for capturing images/video with highest accuracy of frames per second and eliminating overlapping.

8. A real time, automatic, particle measurement method for a variety of agricultural products and confectionaries having an irregular shape and size, said method comprising the steps of:
sampling of agricultural products and confectionaries sample from an input mail line;
feeding of the drawn agricultural products and confectionaries sample into a particle measurement system, the system comprising a conveyor unit comprising a plurality of multi-speed counter direction conveyors, a camera vision system positioned in proximity to the conveyor unit, said camera vision system comprising a combination of at least one colour camera and at least one monochrome camera with Infra-Red backlight, and an integration system comprising a PLC controller, an interface panel for display of results, and a data acquisition system for storage and reporting of data of the agricultural products and confectionaries sample;
creating a monolayer of the agricultural products and confectionaries sample feed, by the plurality of multi-speed counter direction conveyors;
detecting the particle size of the agricultural products and confectionaries sample, and detect the particle density of the agricultural products and confectionaries sample from the monolayer of the sample, by the camera vision system; and
displaying and storage of data of the agricultural products and confectionaries sample.

9. The method as claimed in claim 8, wherein the method further comprises: providing, by a hopper, a uniform flow of the agricultural products and confectionaries without degradations;
distributing, by a feed vibrator, the agricultural products and confectionaries across the width of the plurality of conveyors of the conveyor unit.

10. The method as claimed in claim 9, the method further comprises:
conveying the agricultural products and confectionaries in opposite direction; and
modulating the speed from first conveyor to the last conveyor by carrying the speed at an incremental rate of depending on the type of product,
wherein the incremental speed down the flow on multi-stage counter direction conveyors reduces the facilitates separation of each particle against other, thereby creating a monolayer for particle size measurement.

11. The method as claimed in any one of claims 8-10, wherein the method further comprises:
convert an image/video captured by the camera vision system into a saturation image;
detect contours of each and every single particle of a tobacco sample or each and every single product of the agricultural products and confectionaries sample; and
measure the detected particles in terms of pixels and store them.

12. The method as claimed in claim 8, wherein the method facilitates fast and non-destructive measurement of particle size and stem content in lamina tobacco.

13. The method as claimed in claim 12, wherein the method comprises:
detecting the particle size of the tobacco sample;
detect the Stem content (Stem In Lamina, Objectionable Stem) in the tobacco sample;
processing through different filters of different sizes like 1’’ size filter, ½’’ size filter, ¼’’;
detecting the particles and segregation of the same, with the help of a predetermined threshold value for a particular category of tobacco during calibration process,
wherein the method further comprises calculating

14. The method as claimed in claim 8, the method further comprising:
controlling and operating as per predetermined sequence with high repeatability and reproducibility,
varying the speed of conveyors for creation of a monolayer, by the conveyor unit is operably coupled to servo motors; and
triggering the at least one colour camera and the at least one monochrome camera for capturing images/video with highest accuracy of frames per second and eliminating overlapping, by an encoder operably coupled to the camera vision system.