Identification of the Images of Chinese Herb Slices with Deep Convolutional Network / 世界科学技术-中医药现代化

ABSTRACT

It is of great importance that deep learning of computer for the automate identification of the two-dimensional image of Chinese herbal slices is valuable in the application to medicine,production and education.Traditional methods usually extract low-level image features for the identification,but they cannot give robust recognition results under complex backgrounds.Therefore,higher level image representation is necessary in the image identification.A public Chinese herbal medicine database was constructed with 50 common categories and 2,554 images in total,for training and evaluating our recognition model.Then,the sofimax loss function was adopted to train the convolutional neural network model.As a result,the convolutional neural network can achieve the average precision of 70％ under all the 50 medicine herbal classes.In conclusion,convolutional neural network can obtain good results in image identification with complex backgrounds and mutually occluded herbal slices,which has promising potential for future applications.