首页 | 本学科首页   官方微博 | 高级检索  
     

基于支持向量机的皮肤显微图像识别
引用本文:赵倩,胡越黎,曹家麟. 基于支持向量机的皮肤显微图像识别[J]. 上海大学学报(自然科学版), 2005, 11(1): 24-27
作者姓名:赵倩  胡越黎  曹家麟
作者单位:上海大学,机电工程与自动化学院,上海,200072;上海大学,机电工程与自动化学院,上海,200072;上海大学,机电工程与自动化学院,上海,200072
基金项目:上海市科委基础研究项目 (0 2DJ1 40 3 4),上海市科委技术攻关项目 (0 2 591 1 3 2 3 )
摘    要:该文针对皮肤显微图像症状识别过程中样本采集困难、数量偏少的实际情况,在皮肤症状识别中引入了一种新的模式识别方法——支持向量机(Support Vector Machines,SVM).该方法基于统计学习理论的原理,较好地解决了小样本的分类问题.文中采用“一对一”的策略解决多类别的SVM分类问题,使用留一法进行交叉验证,并比较了SVM与人工神经网络算法的识别结果.结果表明,SVM算法识别率高(89.35%),且速度快.根据该算法,建立了皮肤症状显微图像识别系统软件的原型.

关 键 词:支持向量机  皮肤显微图像  模式识别  分类
文章编号:1007-2861(2005)01-0024-04
修稿时间:2004-03-17

Automatic Recognition of Microscopic Images of Human Skin Based on Support Vector Machine
ZHAO Qian,HU Yue-li,CAO Jia-lin. Automatic Recognition of Microscopic Images of Human Skin Based on Support Vector Machine[J]. Journal of Shanghai University(Natural Science), 2005, 11(1): 24-27
Authors:ZHAO Qian  HU Yue-li  CAO Jia-lin
Abstract:Traditional recognition methods for microscopic images have satisfactory classification performance only when the number of samples is large enough. However this requirement usually cannot be met. In this paper, a new recognition method based on support vector machines (SVM) is proposed to solve the learning problem with a small sample size. Furthermore, a leave-one-out cross-validation (LOOCV) scheme is employed to test the performance of SVM classification, and the "one-against-one" approach is used to solve multi-class classification problems. Using this new method, cross validation accuracy of 89.35% has been obtained in the classification of microscopic images of human skin, suggesting that the SVM approach is better than that of neural networks.
Keywords:support vector machines  microscopic image of skin  pattern recognition  classification  
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号