Crop Disease Detection by Image Processing Using Modified Alexnet

This paper proposed an intelligent plant disease detection system that uses the modified Alexnet. As a convolutional neural network (CNN), Alexnet is good at objection detection from images. However, plant disease detection by the leaf image is a difficult task compared to traditional object detection. Therefore, Alexnet is modified for the different size images and angles to fit the requirement of a practical scenario. A training corpus gathered from the internet and with human leveling is used to train the detection models. According to the experimental results, the proposed approach achieves a good performance.