Tomato disease degree recognition based on RGB and Lab color space conversion method

Abstract

In this paper, a lightweight convolutional neural network model is proposed to diagnose the disease severity of tomato infection. Different regions of tomato leaf image had obvious threshold differences in Lab color space, and the grading label of disease infection degree of each tomato leaf image was obtained. At the same time, in order to solve the problems of low efficiency and general recognition accuracy of artificial recognition of tomato leaf diseases, and unable to accurately judge the tomato disease grade, this paper proposed a new method based on lightweight convolutional neural network, which selected ShuffleNet V2 as the backbone and applied Attention mechanisms that coordinate channel and spatial bidirectional perception. The results of a large number of cross-validation experiments showed that the accuracy of the network structure in classifying the severity of four common tomato leaf diseases and one healthy leaf infection was 91.817%, and the average accuracy was 85.496%.