Rapid computer vision detection of apple diseases based on AMCFNet

Traditional image processing technology has some difficulties in detecting apple diseases. For example, fruit trees, leaves, and branches can interfere with the detection of apple diseases; different diseases of apples are similar and difficult to distinguish. In order to solve these problems, a convolutional neural network based on adaptive multi-channel feature fusion (AMCFNet) is proposed to detect apple diseases. Firstly, we used K-means algorithm for particle swarm optimization to roughly segment the apple disease image to obtain candidate frames, and then used GrabCut to finely segment the candidate frames to remove the background interference of fruit trees, leaves, and branches. Finally, the segmented apple disease image is input to the AMCFNet for detection. Experiments show that our method has better performance than other algorithms, and can reach an accuracy of 99.25% during testing, and it takes only 2.6 s to detect 100 apples.