Identification of crop diseases using improved convolutional neural networks. Issue 7 (14th October 2020)

• Record Type: Journal Article
• Authors: Wang, Long; Sun, Jun; Wu, Xiaohong; Shen, Jifeng; Lu, Bing; Tan, Wenjun
• Is Part Of: IET computer vision. Volume 14:Issue 7(2020)
• Page Start: 538
• Page End: 545
• Publication Date: 2020-10-14
• Subjects: image recognition -- crops -- image segmentation -- feature extraction -- learning (artificial intelligence) -- plant diseases -- convolutional neural nets; improved convolutional neural networks -- AlexNet -- training speed -- single characteristic scale -- convolutional neural network identification model -- inception module -- dilated convolution -- disease characteristics -- receptive field -- improved model -- optimal recognition model -- segmented dataset -- grey‐scaled dataset -- colour features -- training epochs -- background features -- disease information -- crop disease identification; Computer vision -- Periodicals; Pattern recognition systems -- Periodicals; 006.37
• DOI: 10.1049/iet-cvi.2019.0136
• Languages: English
• ISSNs: 1751-9632

Abstract

Abstract : Conventional AlexNet has the problems of slow training speed, single characteristic scale and low recognition accuracy. To solve these problems, a convolutional neural network identification model based on Inception module and dilated convolution is proposed in this study. The inception module combined with dilated convolution, could extract disease characteristics at different scales and increase the receptive field. By setting different parameters, six improved models were obtained. They were trained to identify 26 diseases of 14 different crops; then the authors selected optimal recognition model. On this basis, the segmented dataset and the grey‐scaled dataset were trained as comparative experiments to explore the influence of background and colour features on the recognition results. After only two training epochs, the improved optimal model could achieve an accuracy of over 95%. Moreover, the final average identification accuracy reached 99.37%. Contrast experiments indicate that colour and background features may influence the recognition effect. The improved model can extract disease information from different scales in the feature map to identify diverse diseases of different crops. The proposed model has faster training speed and higher recognition accuracy than the traditional model, and thus it can provide a reference for crop disease identification in actual production.