Recognition of Easily-confused TCM Herbs Using Hierarchical Clustering Convolutional Neural Network
Using of Chinese Herbal Medicines (CHMs) plays an important role of treatment in Traditional Chinese medicine (TCM). There are many CHMs researches require some instrument to analyze. In addition, they are not very in-depth discussion of easy-confused herbs the recognition. Recently, deep learning have widely used in image recognition. However, this technology is not complete development in the CHMs recognition yet.
In this paper, we propose a vision-based CHMs recognition system using hierarchical clustering convolutional neural networks (CNN). CNN can be used to extract more representative features of the confused herbs by data clustering.In experimental part, our recognition method is evaluated by 24 kinds of herbs which collected by ourselves (Containing 10 easy-confused herbs pairs). Experiments show that CNN method/ is better than other hand-crafted methods, and it can achieve higher accuracy rates using hierarchical clustering. We also explore the impact of four different smartphones on the recognition system, and still get acceptable results. We add others smartphones images and data augmentation method/ to increase training data/ to improve this problem.
Finally, we build a herbs recognition system on the server, and the users can receive information about the herbs which they have them as long as they capture images by smartphones and upload to our system.