首页 | 本学科首页   官方微博 | 高级检索  
     

基于新型特征提取的寄生虫卵图像识别研究
引用本文:罗泽举,宋丽红,伍小明,詹希美.基于新型特征提取的寄生虫卵图像识别研究[J].计算机应用,2007,27(6):1485-1487.
作者姓名:罗泽举  宋丽红  伍小明  詹希美
作者单位:1. 重庆工商大学,计算机科学与信息工程学院,重庆,400067
2. 重庆工商大学,实验实习中心,重庆,400067
3. 中山大学,数学与计算科学学院,广东,广州,510275
4. 中山大学,中山医学院,广东,广州,510080
摘    要:讨论了用支持向量机进行多分类的若干学习策略,提出了一种新型图像特征提取方法,以此来实现对鞭虫等九种寄生虫卵图像自动识别和分类,平均识别率优于传统神经网络,达到了93.9%,为寄生虫卵图像识别提供了一种新方法。

关 键 词:支持向量机  新型特征提取  寄生虫卵识别
文章编号:1001-9081(2007)06-1485-03
收稿时间:2006-12-07
修稿时间:2006-12-07

Study on recognition for parasite ovum images based on new method of feature extraction
LUO Ze-ju,SONG Li-hong,WU Xiao-ming,ZHAN Xi-mei.Study on recognition for parasite ovum images based on new method of feature extraction[J].journal of Computer Applications,2007,27(6):1485-1487.
Authors:LUO Ze-ju  SONG Li-hong  WU Xiao-ming  ZHAN Xi-mei
Affiliation:1. School of Computer Science and Information Engineering, Chongqing Technology and Business University, Chongqing 400067, China; 2. Center of Experiment and Practice, Chongqing Technology and Business University, Chongqing 400067, China; 3. School of Mathematics and Computational Sciences, Sun Yat-sen University, Guangzhou Guangdong 510275, China; 4. School of Pre-clinical Medicine, Sun Yat-sen University, Guangzhou Guangdong 510080, China
Abstract:Several learning strategies about multi-class classification by using Support Vector Machine (SVM) being discussed in this paper, we proposed a new kind of method for images feature extraction, so as to realize recognition and classification automatically for the nine kinds of parasites ovum images such as Trichuris trichiura, etc. The average recognition rate is superior to that of traditional neural network and reaches 93.9%, providing a new method for parasites ovum's images recognition.
Keywords:Support Vector Machines (SVM)  new feature extraction  recognition for parasite ovum
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《计算机应用》浏览原始摘要信息
点击此处可从《计算机应用》下载全文
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