AUTHOR=Li Ping , Jing Rongzhi , Shi Xiaoli 

TITLE=Apple Disease Recognition Based on Convolutional Neural Networks With Modified Softmax

JOURNAL=Frontiers in Plant Science

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/plant-science/articles/10.3389/fpls.2022.820146

DOI=10.3389/fpls.2022.820146

ISSN=1664-462X

ABSTRACT=Accurate and rapid identification of crop diseases is the basis for preventing and treating the crop diseases, and is very significant for assessing disease disaster. Crop disease recognition from its diseased leaf images is one of the interesting research areas in computer and agriculture field. A crop disease recognition method is proposed based on modified convolutional neural networks (MCNN). The method can automatically extract effective characteristics rather than artificial features from the crop disease images. In MCNN, global average pooling operator is employed instead of several fully-connected layers to speedup training model, and modified Softmax classifier is used in the output layer to improve the recognition performance. The modified Softmax classifier uses the modified linear element as the activation function in the hidden layer, and adds the local response normalization in MCNN to avoid the gradient disappearance problem effectively. A series of experiments are conducted on a larger scale disease image dataset. The results show the feasibility of the algorithm.