Identification of grape leaf diseases based on VN-BWT and Siamese DWOAM-DRNet

Abstract

Grape disease image identification plays a crucial role in the field of agricultural production. A grape leaf disease classification architecture was proposed for the problems of complex backgrounds and tiny inter-class differences in natural scene images. First, the binary wavelet transform combined with variable threshold method and NL-means improved MSR algorithm (VN-BWT) was used to enhance the grape leaf image to effectively retain more detailed information. Then, the novel Siamese network (Siamese DWOAM-DRNet) based on the combination of diverse-branch residual module (DRM) and the double-factor weight optimization attention mechanism (DWOAM) was proposed for grape leaf diseases classification. In Siamese DWOAM-DRNet, the DWOAM was designed to assign weights according to different strategies in vertical and horizontal directions, which can effectively improve the disease feature extraction ability and reduce the influence of complex background. Then, the diverse branch block (DBB) was used to build the DRM with residual connection strategy to enrich the feature space and improve the response of the network to the features. Finally, the Siamese network with the joint loss function was proposed to accelerate the convergence of the network and solve the problem of high disease similarity that makes the model difficult to distinguish. Experimental results show that the recognition accuracy of Siamese DWOAM-DRNet reached 93.26%, which outperformed other current identification networks in the comparison experiments. The method also performed well on other datasets, proving that the method has excellent generalization performance, which can be applied to identification of grape leaf diseases and realize their prevention and control.