An Accurate Classification of Rice Diseases Based on ICAI-V4
Open Access
Abstract
Rice is a crucial food crop, but it is frequently affected by diseases during its growth process. Some of the most common diseases include rice blast, flax leaf spot, and bacterial blight. These diseases are widespread, highly infectious, and cause significant damage, posing a major challenge to agricultural development. The main problems in rice disease classification are as follows: (1) The images of rice diseases that were collected contain noise and blurred edges, which can hinder the network’s ability to accurately extract features of the diseases. (2) The classification of disease images is a challenging task due to the high intra-class diversity and inter-class similarity of rice leaf diseases. This paper proposes the Candy algorithm, an image enhancement technique that utilizes improved Canny operator filtering (the gravitational edge detection algorithm) to emphasize the edge features of rice images and minimize the noise present in the images. Additionally, a new neural network (ICAI-V4) is designed based on the Inception-V4 backbone structure, with a coordinate attention mechanism added to enhance feature capture and overall model performance. The INCV backbone structure incorporates Inception-iv and Reduction-iv structures, with the addition of involution to enhance the network’s feature extraction capabilities from a channel perspective. This enables the network to better classify similar images of rice diseases. To address the issue of neuron death caused by the ReLU activation function and improve model robustness, Leaky ReLU is utilized. Our experiments, conducted using the 10-fold cross-validation method and 10,241 images, show that ICAI-V4 has an average classification accuracy of 95.57%. These results indicate the method’s strong performance and feasibility for rice disease classification in real-life scenarios.Keywords
Funding Information
- Scientific research project of education department of Hunan province (21A0179, kq2014160, 2021JJ41087, 61902436, 2019TP1015)
- Changsha Municipal Natural Science Foundation (21A0179, kq2014160, 2021JJ41087, 61902436, 2019TP1015)
- Natural Science Foundation of Hunan Province (21A0179, kq2014160, 2021JJ41087, 61902436, 2019TP1015)
- Natural Science Foundation of China (21A0179, kq2014160, 2021JJ41087, 61902436, 2019TP1015)
- Hunan Key Laboratory of Intelligent Logistics Technology (21A0179, kq2014160, 2021JJ41087, 61902436, 2019TP1015)
This publication has 43 references indexed in Scilit:
- Identification of rice diseases using deep convolutional neural networksNeurocomputing, 2017
- Aggregated Residual Transformations for Deep Neural Networks2017
- An overview of current and potential applications of thermal remote sensing in precision agricultureComputers and Electronics in Agriculture, 2017
- ImageNet classification with deep convolutional neural networksCommunications of the ACM, 2017
- A novel online multi-label classifier for high-speed streaming data applicationsEvolving Systems, 2016
- Deep Residual Learning for Image Recognition2016
- A smart sensor for precision agriculture powered by microbial fuel cells2016
- An improved Canny edge detection algorithm2014
- Rice diseases classification using feature selection and rule generation techniquesComputers and Electronics in Agriculture, 2013
- Image enhancement via adaptive unsharp maskingIEEE Transactions on Image Processing, 2000