Description:FIELD OF THE INVENTION
This invention relates to artificial intelligence-based aloe vera leaf disease detection system.
BACKGROUND OF THE INVENTION
Aloe vera is a widely cultivated plant which is popular for its medicinal and beauty products ranging from skin care to natural health remedies. Still, the cultivation of aloe vera has its challenges. Among these diseases that affect this plant include spot and rust but there are many others. It leads to dark spots on the leaves, and if not checked can affect the growth and general welfare of the plant. Rust however, appears in reddish brown patches that may expand quickly if uncontrolled. In order to maintain the medicinal quality and market value of this herb, it is necessary to have sound leaves.
As such, timely detection and treatment of these diseases is important for maintaining both quality and quantity of Aloe vera plants. For instance, traditional methods relied on expert inspection by eye which was cumbersome, laborious as well as human prone mistakes. Conversely, this may not be possible where crops are grown on large scale basis thereby leading to chances of disease spreading before it can be detected at all.
In this context, there is a pressing need for automated solution that can correctly identify these diseases and inform farmers in real-time. By utilizing machine learning and computer vision techniques, a sturdy disease detection model can be formulated to divide the aloe vera leaf conditions into three classes: aloes_leaf_spot, rust, healthy_leaf. Such a model is capable of improving both efficacy and precision of the disease detection process thus enabling farmers to get timely information for taking remedial measures. This not only helps stop diseases from spreading but also maintains plant health hence retaining their quality and market value. The introduction of this technology may transform the management practices employed in growing Aloe Vera into healthier crops that yield more.
US10552663B2 The disclosure relates to machine learning classification of cells/particles in microscopy images. A method includes inputting an image having invisible features into an initial neural network classifier (INNC) of a convolutional neural network. The INNC is trained using images with ground truth derived from out-of-channel mechanisms. The method includes generating an intermediate classification from the original image. The intermediate classification and the original image are input into a final neural network classifier (FNNC) that comprises one or more bypass layers to feed forward an initial, final classification from a final activation layer to a final convolutional layer thereby bypassing a final pooling layer. The final convolutional layer has an increased kernel size and more filters than the initial convolutional layer. The final classification is generated based on the invisible features in the original image and outputted.
RESEARCH GAP:
1. It is an Educational Tool: Additionally, it has been designed as an educational tool for students and researchers who study agriculture and plant pathology with actual application of computer vision and machine learning.
2. Enhanced Plant Health Management: Optimal health status can be maintained throughout the growth cycle by continually monitoring plants thereby promoting higher yields and quality of Aloe Vera.
CN111369540B The invention discloses a plant leaf disease identification method based on a mask convolutional neural network, which mainly solves the problem of low accuracy in identifying plant leaf diseases in the prior art. The scheme is as follows: enhancing and expanding the original data set to obtain a training set and a testing set; carrying out semantic segmentation on the training set and the test set to obtain corresponding mask sets; a disease feature screening module is added between a full convolution layer and a mask branch of the model, and a training set and a mask set are input into a network for training to obtain target classification and target detection results; taking a feature map belonging to the disease blade in the target classification result as the input of a mask branch, and obtaining a trained model after multiple iterations; inputting the test set into the model, classifying and detecting the targets of the blades, and dividing the blades belonging to the disease category. The invention improves the accuracy of identifying the leaf diseases on the basis of the traditional method, and can be used for identifying and dividing the leaf diseases of plants in agricultural planting.
RESEARCH GAP:
1. Integration with the Internet of Things: This system has to link up with other IoT devices that have to make a complete smart farming solution which shows more information and inputs for managing the farm better.
2. Energy Efficiency: The energy consumption of this system is low due to the Raspberry Pi, consequently, it becomes an energy saving device and can be used in those areas where there is power shortage.
None of the prior art indicate above either alone or in combination with one another disclose what the present invention has disclosed. This invention relates to artificial intelligence based aloe vera leaf disease detection system.
SUMMARY OF THE INVENTION
This summary is provided to introduce a selection of concepts, in a simplified format, that are further described in the detailed description of the invention.
This summary is neither intended to identify key or essential inventive concepts of the invention and nor is it intended for determining the scope of the invention.
To further clarify advantages and features of the present invention, a more particular description of the invention will be rendered by reference to specific embodiments thereof, which is illustrated in the appended drawings. It is appreciated that these drawings depict only typical embodiments of the invention and are therefore not to be considered limiting of its scope. The invention will be described and explained with additional specificity and detail with the accompanying drawings.
Figure 1: General architecture of the device in this context, there is a pressing need for automated solution that can correctly identify these diseases and inform farmers in real-time. By utilizing machine learning and computer vision techniques, a sturdy disease detection model can be formulated to divide the aloe vera leaf conditions into three classes: aloes_leaf_spot, rust, healthy_leaf. Such a model is capable of improving both efficacy and precision of the disease detection process thus enabling farmers to get timely information for taking remedial measures. This not only helps stop diseases from spreading but also maintains plant health hence retaining their quality and market value. The introduction of this technology may transform the management practices employed in growing Aloe Vera into healthier crops that yield more.
Figure 2: Detailed architecture of the system with power management using Raspberry Pi for implementing this disease detection model is a cheaper, mobile and effective method. This is a low-cost, high-performance computer that can be easily deployed in different agricultural settings. Combining with superior camera module, raspberry pi would capture fine-grained images of Aloe vera leaves; then machine learning algorithms will analyze these pictures to find out whether the plants suffer from any diseases or not. For faster image processing, Coral USB Accelerator or Intel Neural Compute Stick 2 can enhance computational capabilities of Raspberry Pi. Real-time monitoring and immediate feedback are essential for timely intervention and disease management using this setup. Since it’s portable, Rasperry Pi can be moved around the farm to monitor different areas ensuring that there are no gaps in coverage and efficient disease detection.
Figure 3: Workflow of the Proposed Image Aloe-vera Plant Leaf Disease Detection Classification System Using ResNet the classification task must be related to a picture data set and it should be identified.
This dataset should also be saved in local storage using an organized format such as class directories.
These images are resized to a certain, typical input size ( like 224x224 pixels) that goes well with the ResNet model.
We will use these normalized images to scale pixel values between 0 and 1.
Rotation of images within specified angles is applied (like ±40 degrees).
Images are given width and height shifts by applying them within a certain percentage range (say ±20%).
Shearing transformations on the other hand are realized through altering the angles of inclination for some pictures within given limits — e.g., ±20 degrees.
Zooming transformations on the other hand occur when we adjust the focal length so that objects appear closer or further away from us. Typically, this kind of works lies within some specific limits – e.g., ±20%.
Horizontal flipping randomly mirrors images around an axis that runs horizontally across their centers
Making sure that each image is grey scale .
Splitting it into training (e.g., 80%), validation (e.g., 10%) and testing (e.g., 10%) sets.
There has to be equal distribution per each subset in order not to introduce bias into this task.
ResNet50 is loaded without its top layers since it comes pre-trained already.
Then, custom layers are added on top of this basic ResNet architecture:GlobalAveragePooling2D: Merge features from the convolutional layers.
Dense Layer 1: Fully connected layer with 1024 nodes and ReLU activation function.
Dense Layer 2: Fully connected layer with 512 units and ReLU activation function.
Output Layer: Fully connected layer with 3 nodes (for 3 classes) and softmax activation function.
After that, optimize the model using a good optimizer like Adam and a loss function as categorical cross-entropy. Next, the model should be trained for a few epochs or in batches on the training subset specifying how many epochs and batch size will be suitable for it.
To avoid overfitting, alter hyperparameters by monitoring performance on the validation subset. Lastly, unfreezing the base ResNet model’s some or all layers fine-tunes them. Compile again at lower learning rate Train once again while taking heed of what is happening in the validation set using training subset data The final evaluation metrics involve checking out how well the model has performed on testing data set.
Provide a classification report and confusion matrix for an in-depth analysis.
Employ the trained model in an edge computing device (e.g., Raspberry Pi, NVIDIA Jetson).
Tweak the model to fit in an edge deployment system (e.g., TensorRT, quantization).
Real-time image processing of images on the edge devices using the inference pipeline.
Ensure that data handling and processing is efficient enough to reduce latency and make it possible for real-time applications.
In addition, this system has other advantages that make it appealing to farmers. This means many units can be deployed across a large farm to monitor numerous plants simultaneously thus making it highly scalable. The low power consumption of Raspberry Pi makes the system energy efficient, hence suitable for use in areas without constant electricity supply. It can easily be used by all types of farmers due to their user-friendly interface irrespective of their technical background. Additionally, if integrated with other IoT devices this system can provide a complete smart farming solution capable of producing vital information and insights that can enhance farm management practices even further. Consequently, with such kind of an approach towards monitoring and managing plant health not only will the quality and yield of Aloe Vera improve but also sustainable agriculture technologies will develop.
BRIEF DESCRIPTION OF THE DRAWINGS
The illustrated embodiments of the subject matter will be understood by reference to the drawings, wherein like parts are designated by like numerals throughout. The following description is intended only by way of example, and simply illustrates certain selected embodiments of devices, systems, and methods that are consistent with the subject matter as claimed herein, wherein:
Figure 1: General architecture of the device
Figure 2: Detailed architecture of the system with power management
Figure 3: Workflow of the Proposed Image Aloe-vera Plant Leaf Disease Detection Classification System Using ResNet
Figure 4: Healthy leaf example
Figure 5: Rust example
Figure 6: Leaf Spot example
The figures depict embodiments of the present subject matter for the purposes of illustration only. A person skilled in the art will easily recognize from the following description that alternative embodiments of the structures and methods illustrated herein may be employed without departing from the principles of the disclosure described herein.
DETAILED DESCRIPTION OF THE INVENTION
The detailed description of various exemplary embodiments of the disclosure is described herein with reference to the accompanying drawings. It should be noted that the embodiments are described herein in such details as to clearly communicate the disclosure. However, the amount of details provided herein is not intended to limit the anticipated variations of embodiments; on the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the scope of the present disclosure as defined by the appended claims.
It is also to be understood that various arrangements may be devised that, although not explicitly described or shown herein, embody the principles of the present disclosure. Moreover, all statements herein reciting principles, aspects, and embodiments of the present disclosure, as well as specific examples, are intended to encompass equivalents thereof.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example 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,” “comprising,” “includes” and/or “including,” when used herein, specify the presence of stated features, integers, steps, operations, elements and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and/or groups thereof.
It should also be noted that in some alternative implementations, the functions/acts noted may occur out of the order noted in the figures. For example, two figures shown in succession may, in fact, be executed concurrently or may sometimes be executed in the reverse order, depending upon the functionality/acts involved.
In addition, the descriptions of "first", "second", “third”, and the like in the present invention are used for the purpose of description only, and are not to be construed as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Thus, features defining "first" and "second" may include at least one of the features, either explicitly or implicitly.
Unless otherwise defined, 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 example embodiments belong. It will be further understood that terms, e.g., those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
Figure 1: General architecture of the device in this context, there is a pressing need for automated solution that can correctly identify these diseases and inform farmers in real-time. By utilizing machine learning and computer vision techniques, a sturdy disease detection model can be formulated to divide the aloe vera leaf conditions into three classes: aloes_leaf_spot, rust, healthy_leaf. Such a model is capable of improving both efficacy and precision of the disease detection process thus enabling farmers to get timely information for taking remedial measures. This not only helps stop diseases from spreading but also maintains plant health hence retaining their quality and market value. The introduction of this technology may transform the management practices employed in growing Aloe Vera into healthier crops that yield more.
Figure 2: Detailed architecture of the system with power management using Raspberry Pi for implementing this disease detection model is a cheaper, mobile and effective method. This is a low-cost, high-performance computer that can be easily deployed in different agricultural settings. Combining with superior camera module, raspberry pi would capture fine-grained images of Aloe vera leaves; then machine learning algorithms will analyze these pictures to find out whether the plants suffer from any diseases or not. For faster image processing, Coral USB Accelerator or Intel Neural Compute Stick 2 can enhance computational capabilities of Raspberry Pi. Real-time monitoring and immediate feedback are essential for timely intervention and disease management using this setup. Since it’s portable, Rasperry Pi can be moved around the farm to monitor different areas ensuring that there are no gaps in coverage and efficient disease detection.
Figure 3: Workflow of the Proposed Image Aloe-vera Plant Leaf Disease Detection Classification System Using ResNet the classification task must be related to a picture data set and it should be identified.
This dataset should also be saved in local storage using an organized format such as class directories.
These images are resized to a certain, typical input size ( like 224x224 pixels) that goes well with the ResNet model.
We will use these normalized images to scale pixel values between 0 and 1.
Rotation of images within specified angles is applied (like ±40 degrees).
Images are given width and height shifts by applying them within a certain percentage range (say ±20%).
Shearing transformations on the other hand are realized through altering the angles of inclination for some pictures within given limits — e.g., ±20 degrees.
Zooming transformations on the other hand occur when we adjust the focal length so that objects appear closer or further away from us. Typically, this kind of works lies within some specific limits – e.g., ±20%.
Horizontal flipping randomly mirrors images around an axis that runs horizontally across their centers
Making sure that each image is grey scale .
Splitting it into training (e.g., 80%), validation (e.g., 10%) and testing (e.g., 10%) sets.
There has to be equal distribution per each subset in order not to introduce bias into this task.
ResNet50 is loaded without its top layers since it comes pre-trained already.
Then, custom layers are added on top of this basic ResNet architecture:GlobalAveragePooling2D: Merge features from the convolutional layers.
Dense Layer 1: Fully connected layer with 1024 nodes and ReLU activation function.
Dense Layer 2: Fully connected layer with 512 units and ReLU activation function.
Output Layer: Fully connected layer with 3 nodes (for 3 classes) and softmax activation function.
After that, optimize the model using a good optimizer like Adam and a loss function as categorical cross-entropy. Next, the model should be trained for a few epochs or in batches on the training subset specifying how many epochs and batch size will be suitable for it.
To avoid overfitting, alter hyperparameters by monitoring performance on the validation subset. Lastly, unfreezing the base ResNet model’s some or all layers fine-tunes them. Compile again at lower learning rate Train once again while taking heed of what is happening in the validation set using training subset data The final evaluation metrics involve checking out how well the model has performed on testing data set.
Provide a classification report and confusion matrix for an in-depth analysis.
Employ the trained model in an edge computing device (e.g., Raspberry Pi, NVIDIA Jetson).
Tweak the model to fit in an edge deployment system (e.g., TensorRT, quantization).
Real-time image processing of images on the edge devices using the inference pipeline.
Ensure that data handling and processing is efficient enough to reduce latency and make it possible for real-time applications.
In addition, this system has other advantages that make it appealing to farmers. This means many units can be deployed across a large farm to monitor numerous plants simultaneously thus making it highly scalable. The low power consumption of Raspberry Pi makes the system energy efficient, hence suitable for use in areas without constant electricity supply. It can easily be used by all types of farmers due to their user-friendly interface irrespective of their technical background. Additionally, if integrated with other IoT devices this system can provide a complete smart farming solution capable of producing vital information and insights that can enhance farm management practices even further. Consequently, with such kind of an approach towards monitoring and managing plant health not only will the quality and yield of Aloe Vera improve but also sustainable agriculture technologies will develop.
An Artificial Intelligence based Aloe Vera leaf disease detection system comprises a plurality of AloeVision (1.1, 1.2, 1.N), Information Collector (2), Coud Server (3), LCD Screen for Output (4), Wifi Module (5), Camera (6), Lidar Sensor (7), Heatsinks or Cooling Fan (8), Neural Stick (9), Raspberry Pi (10), Microcontroller (11), Keyboard (12), Mouse (13), 12v 3amp Lithium Polymer (Battery) (14), Charger (15), AC Outlet (16) and Changing Current (17) wherein the camera is use for capture all images and give real time information; wherein the low power consumption of the microprocessor makes the system energy efficient, hence suitable for use in areas without constant electricity supply; It is used by all types of farmers due to their user-friendly interface irrespective of their technical background.
In another embodiment The low power consumption of the microprocessor makes the system energy efficient, hence suitable for use in areas without constant electricity supply; It can easily be used by all types of farmers due to their user-friendly interface irrespective of their technical background.
In another embodiment By utilizing the machine learning algorithm and computer vision techniques, a sturdy disease detection model can be formulated to divide the aloe vera leaf conditions into three classes: aloes_leaf_spot, rust, healthy_leaf.
In another embodiment For faster image processing, Coral USB Accelerator or Intel Neural Compute Stick 2 can enhance computational capabilities of microprocessor.
In another embodiment the dataset should also be saved in local storage using an organized format such as class directories.
In another embodiment the images are resized to a certain, typical input size (like 224x224 pixels) that goes well with the ResNet model; Real-time image processing of images on the edge devices using the inference pipeline.
In another embodiment provide automated solution can correctly identify these diseases and inform farmers in real-time for Aloe vera plants.
In another embodiment utilizes machine learning and computer vision techniques, a sturdy disease detection model can be formulated to divide the aloe vera leaf conditions into three classes: aloes_leaf_spot, rust, healthy_leaf.
In another embodiment strengthen capable of improving both efficacy and precision of the disease detection process thus enabling farmers to get timely information for taking remedial measures.
ADVANTAGES OF THE INVENTION
Raspberry Pi: Cheap Solution with High Impact
Detects Diseases in Real-Time: Making it easy for decision makers to take action at the right time.
Handy: A small circuit board, housing a camera, can be attached anywhere around the farm to allow for total surveillance.
Precision and Coherence: Eliminates cases of human errors that might arise from visual inspection and offers high accuracy disease detection via machine learning model.
Can Grow with You: By deploying several units in different sections of the field, a system can handle huge number of plants.
Easy-to-Use Interface: Farmers do not need much technical know-how as this system comes with an intuitive interface that is easily set up.
, Claims:1. An Artificial Intelligence based Aloe Vera leaf disease detection system comprises a plurality of AloeVision (1.1, 1.2, 1.N), Information Collector (2), Coud Server (3), LCD Screen for Output (4), Wifi Module (5), Camera (6), Lidar Sensor (7), Heatsinks or Cooling Fan (8), Neural Stick (9), Raspberry Pi (10), Microcontroller (11), Keyboard (12), Mouse (13), 12v 3amp Lithium Polymer (Battery) (14), Charger (15), AC Outlet (16) and Changing Current (17) wherein the camera is use for capture all images and give real time information;
wherein the low power consumption of the microprocessor makes the system energy efficient, hence suitable for use in areas without constant electricity supply; It is used by all types of farmers due to their user-friendly interface irrespective of their technical background.
2. The system as claimed in claim 1, wherein by utilizing the machine learning algorithm and computer vision techniques, a sturdy disease detection model can be formulated to divide the aloe vera leaf conditions into three classes: aloes_leaf_spot, rust, healthy_leaf.
3. The system as claimed in claim 1, wherein for faster image processing, Coral USB Accelerator or Intel Neural Compute Stick 2 can enhance computational capabilities of microprocessor.
4. The system as claimed in claim 1, wherein the dataset is saved in local storage using an organized format such as class directories.
5. The system as claimed in claim 1, wherein the images are resized to a certain, typical input size (like 224x224 pixels) that goes well with the ResNet model; Real-time image processing of images on the edge devices using the inference pipeline.
6. The system as claimed in claim 1, wherein, provide automated solution can correctly identify these diseases and inform farmers in real-time for Aloe vera plants.
7. The system as claimed in claim 1, wherein utilizes machine learning and computer vision techniques, a sturdy disease detection model is formulated to divide the aloe vera leaf conditions into three classes: aloes_leaf_spot, rust, healthy_leaf.
8. The system as claimed in claim 1, wherein, strengthen capable of improving both efficacy and precision of the disease detection process thus enabling farmers to get timely information for taking remedial measures.