Abstract
Chinese herbal medicine (CHM) have a long history, a wide variety, and similar shapes, which lead to the difficulty and low efficiency of traditional CHM identification methods (mainly including original identification, morphological identification, microscopic identification, and physical and chemical identification). In view of the above problems, this paper proposes an improved method based on the traditional convolutional neural network VGG. First of all, this paper is no longer limited to the Conv-Batch Normalization (BN)-Max Pooling network structure model, but uses three (Conv-BN, Conv-Max Pooling and Conv-BN-Max Pooling) interlaced network structures. Second, we use GAP to connect the convolutional and fully connected layers (FC). The experimental results show that compared with the Conv-BN-Max Pooling network structure, using the above improved network structure can improve the recognition accuracy rate by 3.3% (Epoch 100), and finally achieve a correct recognition rate of 97.86% for 12 traditional Chinese medicine images, which proves that the proposed improved method has certain advantages compared with other network structures, and explores new ideas for the modern identification of Chinese medicinal materials.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: International Journal of Applied Mathematics and Machine Learning
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
