关键词: 农作物病理分类, 卷积神经网络, 特征融合

Abstract: The rapid and effective detection of crop pathology is of great significance to agriculture. It can not only improve the efficiency of automated pathology recognition, but also increase crop yields. This paper takes potato, tomato and other crops as the pathological research object, and proposes a crop pathological classification model based on convolutional neural network MFCPNet. First, build a deep convolutional neural network model, which is constructed through a convolutional layer, an activation layer, and a fully connected layer of a pooling layer. Then, the extracted image pathological features are fused with multiple features to effectively enhance the feature richness of crop pathology.At the same time, the original data set is enhanced to eliminate the problem of uneven sample distribution. The results show that the standards of the proposed crop pathology classification model are better than the AlexNet, VGG16 and VGG19 models, reaching an accuracy of 94.92%. At the same time, it eliminates the need for manual construction of complex feature projects, which has a certain value in promoting agricultural automation.

Key words: crop pathology classification, convolutional neural network, feature fusion