| Features Selection for Skin
Micro-Image Symptomatic Recognition |
| |
| 作者姓名： | " target="_blank">HU Yue-li CAO Jia-lin" target="_blank">CAO Jia-lin ZHAO Qian" target="_blank">ZHAO Qian FENG Xu" target="_blank">FENG Xu |
| |
| 作者单位： | HU Yue-li（School of Mechatronical Engineering and Automation,
Shanghai University, Shanghai 200072, China）
CAO Jia-lin（School of Mechatronical Engineering and Automation,
Shanghai University, Shanghai 200072, China）
ZHAO Qian（School of Mechatronical Engineering and Automation,
Shanghai University, Shanghai 200072, China）
FENG Xu（School of Mechatronical Engineering and Automation,
Shanghai University, Shanghai 200072, China） |
| |
| 基金项目： | 上海市科委资助项目，上海市科委资助项目 |
| |
| 摘 要： |
|
Features Selection for Skin Micro-Image Symptomatic Recognition |
| |
| HU Yue-li,CAO Jia-lin,ZHAO Qian,FENG Xu.Features Selection for Skin
Micro-Image Symptomatic Recognition[J].Journal of Shanghai University(Natural Science),2004,10(Z1):123-128. |
| |
| Authors: | HU Yue-li CAO Jia-lin ZHAO Qian FENG Xu |
| |
| Abstract: | Automatic recognition of skin micro-image symptom is important in skin diagnosis and treatment. Feature selection is to improve the classification performance of skin micro-image symptom.This paper proposes a hybrid approach based on the support vector machine (SVM) technique and genetic algorithm (GA) to select an optimum feature subset from the feature group extracted from the skin micro-images. An adaptive GA is introduced for maintaining the convergence rate. With the proposed method, the average cross validation accuracy is increased from 88.25% using all features to 96.92 % using only selected features provided by a classifier for classification of 5 classes of skin symptoms. The experimental results are satisfactory. |
| |
| Keywords: | feature selection adaptive genetic algorithm support vector machine (SVM) skin micro-image pattern recognition |
| 本文献已被 万方数据 等数据库收录！ |
|
