Recognition of Tomato Leaf Diseases Based on DIMPCNET

The identification of tomato leaf diseases is easily affected by complex backgrounds, small differences between different diseases, and large the same diseases. Therefore, we propose a novel classification network for disease, Dense Inception MobileNet-V2 parallel convolutional block attention module (DIMPCNET). To begin, collected total 1256 original images 5 expanded them to 8190 using data enhancement techniques. Next, an improved bilateral filtering threshold function (IBFTF) algorithm designed effectively remove noise. Then, neural (DI) was alleviate problem intra-class inter-class differences. (PCBAM) added reduce impact backgrounds. Finally, experimental results show that recognition accuracy F1-score obtained DIMPCNET are 94.44% 0.9475. loss approximately 0.28%. This method most advanced provides new idea crop such as tomatoes, development smart agriculture.