Identification of Plant Disease from Leaf Images Based on Convolutional Neural Network
IEEE BASE PAPER TITLE:
Identification of Plant Disease from Leaf Images Based on Convolutional Neural Network
(or)
OUR PROPOSED PROJECT TITLE:
Plant Disease Classification using Deep Learning
IEEE BASE PAPER ABSTRACT:
With the development of plant phenomics, the identification of plant diseases from leaf images has become an effective and economic approach in plant disease science. Among the methods of plant diseases identification, the convolutional neural network (CNN) is the most popular one for its superior performance. However, CNN’s representation power is still a challenge in dealing with small datasets, which greatly affects its popularization. In this work, we propose a new method, namely PiTLiD, based on pretrained Inception-V3 convolutional neural network and transfer learning to identify plant leaf diseases from phenotype data of plant leaf with small sample size. To evaluate the robustness of the proposed method, the experiments on several datasets with small-scale samples were implemented. The results show that PiTLiD performs better than compared methods. This study provides a plant disease identification tool based on a deep learning algorithm for plant phenomics.
PROJECT OUTPUT VIDEO:
ALGORITHM / MODEL USED:
AlexNet CNN Model.
OUR PROPOSED PROJECT ABSTRACT:
The project titled “Identification of Plant Disease from Leaf Images Based on Convolutional Neural Network” leverages the power of deep learning techniques, specifically the AlexNet Convolutional Neural Network (CNN) model, implemented in MATLAB, to address the critical challenge of automated plant disease identification. With an impressive achieved accuracy of 99.61%, this project demonstrates a robust solution for early disease detection in various crops. The dataset utilized for training and evaluation encompasses ten distinct plant disease classes: Apple Black Rot, Apple Rust, Cherry Powdery Mildew, Corn Leaf blight, Grape Black Rot, Peach Bacterial Spot, Potato Early Blight, Soybean Healthy, Strawberry Leaf Scorch, and Tomato Late Blight. The availability of this diverse dataset enables the model to accurately classify a wide range of plant diseases, aiding in prompt and effective disease management. The initial phase comprises capturing leaf images of diseased plants. These images serve as the primary input for disease classification. In the preprocessing stage, several essential steps are undertaken to enhance the quality of the input images. Following preprocessing, the project leverages the powerful AlexNet CNN model to extract meaningful features from the preprocessed leaf images and subsequently classify them into one of the ten plant disease categories. To fine-tune the model’s performance, essential hyperparameters such as epochs, learning rate, batch size, and optimizer (Stochastic Gradient Descent with Momentum – SGDM) are carefully tuned during the training phase. This optimization process contributes significantly to achieving the remarkable accuracy rate of 99.61%. The project’s success is quantified through various performance metrics, including accuracy, error rate, precision, recall, specificity, F1-score, and Matthews Correlation Coefficient (MCC). These metrics collectively gauge the model’s ability to accurately identify and differentiate between plant diseases, providing valuable insights into its real-world applicability. In summary, the “Identification of Plant Disease from Leaf Images Based on Convolutional Neural Network” project showcases the potential of deep learning, specifically the AlexNet CNN model, to revolutionize agriculture by automating disease detection and assisting farmers in timely disease management. With its outstanding accuracy and comprehensive evaluation metrics, this project offers a robust and practical solution for early disease identification in a variety of crops, ultimately contributing to increased crop yield and food security.
SYSTEM REQUIREMENTS:
HARDWARE REQUIREMENTS:
- System : Pentium i3 Processor.
- Hard Disk : 500 GB.
- Monitor : 15’’ LED.
- Input Devices : Keyboard, Mouse.
- Ram : 8 GB.
SOFTWARE REQUIREMENTS:
- Operating system : Windows 10 Pro.
- Coding Language : MATLAB
- Tool : MATLABR2021A
REFERENCE:
Kangchen Liu and Xiujun Zhang, “PiTLiD: Identification of Plant Disease From Leaf Images Based on Convolutional Neural Network”, IEEE/ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGYAND BIOINFORMATICS, VOL. 20, NO. 2, MARCH/APRIL 2023.