Publications by authors named "Er-Yang Huan"
Multilevel and Multiscale Feature Aggregation in Deep Networks for Facial Constitution Classification.
Comput Math Methods Med
August 2020
Constitution classification is the basis and core content of TCM constitution research. In order to improve the accuracy of constitution classification, this paper proposes a multilevel and multiscale features aggregation method within the convolutional neural network, which consists of four steps. First, it uses the pretrained VGG16 as the basic network and then refines the network structure through supervised feature learning so as to capture local image features.
View Article and Find Full Text PDFDeep Convolutional Neural Networks for Classifying Body Constitution Based on Face Image.
Comput Math Methods Med
August 2018
Article Synopsis
- Body constitution classification is a key area in traditional Chinese medicine (TCM), which aims to categorize individuals based on their unique physical characteristics.
- Traditional methods like questionnaires are often slow and less accurate, prompting the development of a new technique.
- The paper introduces a deep convolutional neural network algorithm that analyzes facial images to classify body constitution types, achieving a classification accuracy of 65.29%, which has been well-received by practitioners in the field.