INNOVATIVE DATA FUSION TECHNIQUE ENHANCES TOMATO DISEASE CLASSIFICATION MODELS

Abstract

ABSTRACT “INNOVATIVE DATA FUSION TECHNIQUE ENHANCES TOMATO DISEASE CLASSIFICATION MODELS” The present invention provides Innovative data fusion technique enhances tomato disease classification models. The method involves splitting images of diseased tomato leaves and fusing different halves to create synthetic samples, simulating multiple diseases on the same leaf. This approach addresses the challenge of overlapping disease traits, improving the accuracy and reliability of classification models. The system integrates deep learning architecture using TensorFlow Keras, featuring convolutional layers for feature extraction and a Softmax output for multi-disease classification. Data augmentation techniques, such as image flipping and rotation, are employed to enhance the training dataset, preventing overfitting and improving generalization. Performance evaluation uses balanced metrics like accuracy, precision, recall, and F1 score to ensure robust classification of multiple diseases, providing a valuable tool for real-world agricultural applications. Figure 1

Specification

Description:TECHNICAL FIELD
[0001] The present invention relates to the field of artificial intelligence and agricultural systems, and more particularly, the present invention relates to the innovative data fusion technique enhances tomato disease classification models.
BACKGROUND ART
[0002] The following discussion of the background of the invention is intended to facilitate an understanding of the present invention. However, it should be appreciated that the discussion is not an acknowledgment or admission that any of the material referred to was published, known, or part of the common general knowledge in any jurisdiction as of the application's priority date. The details provided herein the background if belongs to any publication is taken only as a reference for describing the problems, in general terminologies or principles or both of science and technology in the associated prior art.
[0003] Tomato (Solanum lycopersicum), a globally significant crop, is plagued by numerous diseases that severely impact its leaves, reducing health and productivity. These diseases often manifest through symptoms like discoloration, lesions, spots, and deformities triggered by various pathogens such as fungi, bacteria, viruses, and environmental factors. Examples include bacterial spots, early blight, target spots, late blight, leaf mold, yellow leaf curl virus, septoria leaf spots, and spotted spider mites. Understanding and effectively managing these diseases are crucial for ensuring sustainable tomato production, given the vital role of tomato leaves in photosynthesis and overall plant health. Reviewing previous research has overwhelmingly demonstrated that most deep-learning studies focused on predicting tomato diseases have typically centered on predicting a single disease in each test. We found that the monopoly detection mechanisms mostly predicted different diseases in the presence of another disease on the same tomato leaf
[0004] In light of the foregoing, there is a need for Innovative data fusion technique enhances tomato disease classification models that overcomes problems prevalent in the prior art associated with the traditionally available method or system, of the above-mentioned inventions that can be used with the presented disclosed technique with or without modification.
[0005] All publications herein are incorporated by reference to the same extent as if each individual publication or patent application were specifically and individually indicated to be incorporated by reference. Where a definition or use of a term in an incorporated reference is inconsistent or contrary to the definition of that term provided herein, the definition of that term provided herein applies, and the definition of that term in the reference does not apply.
OBJECTS OF THE INVENTION
[0006] The principal object of the present invention is to overcome the disadvantages of the prior art by providing Innovative data fusion technique enhances tomato disease classification models.
[0007] Another object of the present invention is to provide Innovative data fusion technique enhances tomato disease classification models that identifies multiple diseases on a tomato leaf.
[0008] Another object of the present invention is to provide Innovative data fusion technique enhances tomato disease classification models that propose a four-way method: Data Acquisition, Preprocessing, Data Splitting and Fusing, and Classification.
[0009] Another object of the present invention is to provide Innovative data fusion technique enhances tomato disease classification models that utilizes TensorFlow's Keras, which has an intuitive and powerful framework commonly used to build classification models
[0010] The foregoing and other objects of the present invention will become readily apparent upon further review of the following detailed description of the embodiments as illustrated in the accompanying drawings.
SUMMARY OF THE INVENTION
[0011] The present invention relates to Innovative data fusion technique enhances tomato disease classification models. We proposed an augmentation process on the PlantVillage dataset to confuse the existing prediction tools to identify multiple diseases on a tomato leaf. We propose a four-way method for this work: Data Acquisition, Preprocessing, Data Splitting and Fusing, and Classification. The final stage of the classification utilizes TensorFlow's Keras, which has an intuitive and powerful framework commonly used to build classification models, as shown in Figure 1.
[0012] Figure 2 shows the complete overall working details of our proposed work. First, we collect and send tomato leaves, which are subject to diagnosis, on a local or cloud server using Amazon Web Service (AWS). A single disease or multiple diseases may infect these leaves. After predicting leaves from nearby agriculture fields, our proposed system multicast the diagnosis details to the registered farmers. The details include the percentage of a single disease or multiple diseases on a tomato leaf and several overall diseases nearby.
[0013] While the invention has been described and shown with reference to the preferred embodiment, it will be apparent that variations might be possible that would fall within the scope of the present invention.
BRIEF DESCRIPTION OF DRAWINGS
[0014] So that the manner in which the above-recited features of the present invention can be understood in detail, a more particular description of the invention, briefly summarized above, may have been referred by embodiments, some of which are illustrated in the appended drawings. It is to be noted, however, that the appended drawings illustrate only typical embodiments of this invention and are therefore not to be considered limiting of its scope, for the invention may admit to other equally effective embodiments.
[0015] These and other features, benefits, and advantages of the present invention will become apparent by reference to the following text figure, with like reference numbers referring to like structures across the views, wherein:
[0016] Figure 1: Technical details of the proposed innovation.
[0017] Figure 2: Workflow of the proposed Innovation.
DETAILED DESCRIPTION OF THE INVENTION
[0018] While the present invention is described herein by way of example using embodiments and illustrative drawings, those skilled in the art will recognize that the invention is not limited to the embodiments of drawing or drawings described and are not intended to represent the scale of the various components. Further, some components that may form a part of the invention may not be illustrated in certain figures, for ease of illustration, and such omissions do not limit the embodiments outlined in any way. It should be understood that the drawings and the detailed description thereto are not intended to limit the invention to the particular form disclosed, but on the contrary, the invention is to cover all modifications, equivalents, and alternatives falling within the scope of the present invention as defined by the appended claim.
[0019] As used throughout this description, the word "may" is used in a permissive sense (i.e. meaning having the potential to), rather than the mandatory sense, (i.e. meaning must). Further, the words "a" or "an" mean "at least one" and the word "plurality" means "one or more" unless otherwise mentioned. Furthermore, the terminology and phraseology used herein are solely used for descriptive purposes and should not be construed as limiting in scope. Language such as "including," "comprising," "having," "containing," or "involving," and variations thereof, is intended to be broad and encompass the subject matter listed thereafter, equivalents, and additional subject matter not recited, and is not intended to exclude other additives, components, integers, or steps. Likewise, the term "comprising" is considered synonymous with the terms "including" or "containing" for applicable legal purposes. Any discussion of documents, acts, materials, devices, articles, and the like are included in the specification solely for the purpose of providing a context for the present invention. It is not suggested or represented that any or all these matters form part of the prior art base or were common general knowledge in the field relevant to the present invention.
[0020] In this disclosure, whenever a composition or an element or a group of elements is preceded with the transitional phrase "comprising", it is understood that we also contemplate the same composition, element, or group of elements with transitional phrases "consisting of", "consisting", "selected from the group of consisting of, "including", or "is" preceding the recitation of the composition, element or group of elements and vice versa.
[0021] The present invention is described hereinafter by various embodiments with reference to the accompanying drawing, wherein reference numerals used in the accompanying drawing correspond to the like elements throughout the description. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiment set forth herein. Rather, the embodiment is provided so that this disclosure will be thorough and complete and will fully convey the scope of the invention to those skilled in the art. In the following detailed description, numeric values and ranges are provided for various aspects of the implementations described. These values and ranges are to be treated as examples only and are not intended to limit the scope of the claims. In addition, several materials are identified as suitable for various facets of the implementations. These materials are to be treated as exemplary and are not intended to limit the scope of the invention.
[0022] The present invention relates to Innovative data fusion technique enhances tomato disease classification models.
[0023] The present invention relates to Innovative data fusion technique enhances tomato disease classification models. We proposed an augmentation process on the PlantVillage dataset to confuse the existing prediction tools to identify multiple diseases on a tomato leaf. We propose a four-way method for this work: Data Acquisition, Preprocessing, Data Splitting and Fusing, and Classification. The final stage of the classification utilizes TensorFlow's Keras, which has an intuitive and powerful framework commonly used to build classification models, as shown in Figure 1.
[0024] Figure 2 shows the complete overall working details of our proposed work. First, we collect and send tomato leaves, which are subject to diagnosis, on a local or cloud server using Amazon Web Service (AWS). A single disease or multiple diseases may infect these leaves. After predicting leaves from nearby agriculture fields, our proposed system multicast the diagnosis details to the registered farmers. The details include the percentage of a single disease or multiple diseases on a tomato leaf and several overall diseases nearby.
[0025] The methodology detailed in the paper [2] presented how the Gabor wavelet transformation technique was employed to extract distinctive features that helped to identify diseases in tomato leaves. Subsequently, these extracted features are input into a Support Vector Machine (SVM) classifier for training, enabling the determination of the specific disease affecting the tomato leaves. Before the feature extraction, the preprocessing stage involves image resizing, noise reduction, and background elimination tasks. The research used the Gabor transformation to capture textual patterns inherent in the affected leaves and extract relevant features. Disease classification was conducted using SVM with varying kernel functions.
[0026] There was cross-validation on performance evaluation. The SVM ROC curve using the invmult kernel produced an AUC of 0.90705, while the one using the Laplacian kernel produced an AUC of 0.99679. Experimental results indicate an impressive accuracy rate of 99.5% achieved by the proposed system. However, it is necessary to note the utilization of Gabor transformation for feature extraction comes with the limitation of computational intensiveness.
[0027] In the paper [3], the authors employed a dataset comprising 9000 images of infected and healthy tomato leaves. All images were produced within a controlled laboratory environment. This dataset, sourced from the PlantVillage repository, was harnessed to classify five distinct diseases: leaf curl, bacterial spot, septoria leaf spot, early blight, and leaf mold. A comprehensive color model was utilized for disease spot classification, while a grayscale model was employed to capture the underlying leaf shapes and visual disease patterns. The results revealed that the full-color model achieved superior accuracy compared to the grayscale model.
[0028] However, it is noteworthy that the captured results were obtained under precisely controlled conditions within the PlantVillage dataset, thereby introducing a potential limitation to the model's applicability in a more diverse setting. In the paper [4], the author used a dataset comprising 2,779 images from Google Images. These images encompassed various instances of hornworms, powdery mildew, cutworms, early blight, and whiteflies. Notably, each disease category contained 550 images. This quantity is considered limited for robust training, potentially giving rise to overfitting concerns. The author employed data augmentation techniques to mitigate the overfitting challenge, including vertical flips and random scaling.
[0029] These techniques introduce diversity and variability into the dataset, contributing to a more generalized and resilient model. While Convolutional Neural Networks (CNNs) are well-suited for deciphering image content, it is worth noting that training a CNN from scratch demands substantial computational resources and a vast dataset. The author opted for a transfer learning approach, utilizing the Google Inception model as a foundation. By leveraging pre-trained weights and features from the Tensorflow Inception V3 model, the author could capitalize on its learned representations and optimize the training process, effectively sidestepping the need for extensive data and computational power after the model achieved an accuracy of 88.9%. The dataset for the paper [5] was obtained from Ehime University in Matsuyama. The scientists developed several simultaneous convolutional neural networks with various topologies to identify tomato leaf disease.
[0030] To significantly improve the network's performance, they used the activation layers Swish, LeakyReLU-Swish, ReLU-Swish, Elu-Swish, and ClippedReLU-Swish in addition to the Batch Normalization-Instance Normalisation layer. That allowed them to achieve classification accuracy of over 99.0% with training datasets, 97.5% with validation datasets, and 98.0% with testing datasets. Although different performance metrics were observed, none of the suggested networks overfit the validation dataset. They also employed a variety of methods to visualize network performance. That showed how the networks (Network 1, Network 2, Network 3, Network 4, Network 5) learn from the training dataset and could show infected leaf areas with high confidence scores under actual circumstances. In terms of network stability and illness location visualization, Network 1 performed the best.
[0031] The shortcomings of Networks 4 and 5 in predicting the Healthy class could be resolved by computing, summarising, and rating the output of a number of parallel convolutional neural networks[5]. In paper [6], The study proposed a lightweight custom convolutional neural network (CNN) model and utilized transfer learning (TL)-based models VGG-16 and VGG-19 to classify tomato leaf diseases. In that study, eleven classes, one of which is healthy, are used to simulate various tomato leaf diseases. In addition, an ablation study was performed to find the optimal parameters for the proposed model. Furthermore, evaluation metrics were used to analyze and compare the performance of the proposed model with the TL-based model. The proposed model achieved the highest accuracy and recall of 95.00% of all the models by applying data augmentation techniques. Finally, the best-performing model was utilized to construct a Web-based and Android-based end-to-end (E2E) system for tomato cultivators to classify tomato leaf disease.
[0032] We introduce a novel "data fusion" technique to enhance disease classification in tomato plants. This technique involves splitting and fusing distinct disease-specific traits from different halves of leaf images to generate synthetic samples. This approach addresses the challenge of overlapping disease traits, which can lead to misclassification. Also, the data fusion technique generates complex structures by combining different diseased leaf halves, creating a diverse set of training samples. This diversity can help the deep learning model better learn and distinguish between diseases with overlapping or similar symptoms. Unlike most existing studies focusing on detecting a single disease per leaf, the proposed approach aims to detect and classify multiple diseases on the same leaf. It is a more realistic scenario in real-world applications, where plants can simultaneously be affected by various diseases. Nevertheless, the proposed solution incorporates data augmentation techniques, such as image flipping and rotation, to further increase the diversity of the training dataset. It helps improve the model's generalization ability and prevent overfitting.
[0033] SomeoftheEconomicPotentialandCommercialApplicationsofthisresearchareasbelow:
[0034] Plant Disease Research: The data fusion technique and the ability to analyze disease interactions can contribute to plant disease research, aiding in understanding disease mechanisms,developingtargetedtreatments,andbreedingdisease-resistantvarieties.
[0035] Crop Insurance and Risk Assessment: Accurate disease classification can assist crop insurance providers and risk assessment firms in evaluating disease-related risks and estimating potential losses.
[0036] Agritech Startups and Established Companies: The proposed solution presents an opportunity for agritech startups and established companies to develop and commercialize innovative products and services for disease monitoring and management in the agricultural sector.
[0037] Data Fusion Technique:
- The proposed "data fusion" technique involves splitting leaf images from different disease classes into halves and then fusing these split halves from different disease classes to create synthetic images with combined disease traits.
- This approach is novel as it aims to replicate the complex interactions and visual manifestations of multiple diseases affecting the same leaf, which is a more realistic scenario compared to existing solutions that primarily focus on detecting a single disease per leaf.
- The data fusion technique generates synthetic training data that is more diverse and representative of real-world scenarios, potentially improving the model's ability to generalize and classify multiple diseases accurately. 2. Deep Learning Model Architecture for Multi-Disease Classification:
- The proposed solution utilizes a deep learning model based on TensorFlow Keras, specifically designed to classify multiple diseases present on the same leaf image.
- The model architecture includes convolutional layers for feature extraction, dense layers for higher-level representations, and an output layer with a Softmax activation function to produce class probabilities for multiple diseases.
- The model is trained on the fused images generated by the data fusion technique, enabling it to learn and distinguish the combined disease traits more effectively.
- Existing deep learning models for plant disease classification are typically designed to detect and classify a single disease per leaf, and may not be optimized to handle the complexities of multiple diseases on the same leaf. 3. Balanced Performance Metrics for Multi-Disease Classification:
- The proposed solution evaluates the model's performance using a combination of metrics, including accuracy, precision, recall, and the F1 score.
- These metrics are essential for assessing the model's ability to correctly classify positive instances (diseased leaves) while minimizing false positives and false negatives in the context of multi-disease classification.
- The research paper highlights the importance of balancing precision and recall, as achieving high precision alone may not be sufficient for practical applications where capturing all positive instances (high recall) is crucial.
- Existing solutions for plant disease classification often focus primarily on accuracy or a single performance metric, which may not provide a comprehensive evaluation of the model's capabilities in multi-disease scenarios.
[0038] Various modifications to these embodiments are apparent to those skilled in the art from the description and the accompanying drawings. The principles associated with the various embodiments described herein may be applied to other embodiments. Therefore, the description is not intended to be limited to the 5 embodiments shown along with the accompanying drawings but is to be providing the broadest scope consistent with the principles and the novel and inventive features disclosed or suggested herein. Accordingly, the invention is anticipated to hold on to all other such alternatives, modifications, and variations that fall within the scope of the present invention and appended claims. , Claims:CLAIMS
We Claim:
1) A tomato disease classification system utilizing a data fusion technique, the system comprising:
- a process of splitting leaf images infected with multiple diseases into halves, and
- fusing the split halves from different disease classes to create synthetic images for deep learning model training, enhancing the system's ability to detect multiple diseases on a single tomato leaf.
2) The system as claimed in claim 1, wherein the fused synthetic images exhibit complex disease traits that replicate real-world scenarios of overlapping diseases, improving the classification accuracy for multiple diseases simultaneously affecting tomato leaves.
3) system as claimed in claim 1, wherein the system further comprising a data augmentation process including image flipping, rotation, and scaling to increase the diversity of the training dataset, preventing overfitting and improving the generalization ability of the classification model.
4) A tomato leaf disease classification method, the method comprising:
- Acquiring images of diseased tomato leaves;
- Preprocessing the images by resizing, noise reduction, and background elimination;
- Applying Gabor wavelet transformation to extract textural features, and
- Using a deep learning model trained with synthetic data generated through the data fusion technique to classify multiple diseases on the same leaf.
5) The method as claimed in claim 1, wherein the deep learning model architecture includes convolutional layers for feature extraction, dense layers for higher-level representations, and an output layer with Softmax activation for multi-disease classification.
6) A system for classifying tomato leaf diseases, wherein:
- the classification performance is evaluated using balanced performance metrics such as accuracy, precision, recall, and F1 score, ensuring accurate detection of multiple diseases with minimal false positives and false negatives.

Documents