AN Information Filter Based on Reversed Word Segmentation and Complexion Detection

摘要：

The kernel of unhealthy network information filtering is to identify the web page properties.To overcome the shortages of traditional algorithm,we proposed a new method based on text analysis and color recognition.A mathematical model was established which combines text and image to judge the properties of web-pages.The new method dramatically improved the recognition rate and reduced the false accept rate.

关键词： Information filter Word segmenting complexion recognition

作者: Leiyue Yao Jianying Xiong

作者单位: Software Research Center,Jiangxi Blue Sky University,Nanchang,Jiangxi,China Department of Computer Science and Technology,Jiangxi Blue Sky University,Nanchang,Jiangxi,China

会议类型: 国际会议

会议名称: 2008年国际电子商务、工程及科学领域的分布式计算和应用学术研讨会(2008 International Symposium on Distributed Computing and Applications for Business Engineering and Science)

会议地点: 大连

会议语种:英文

页码: 396-399

在线出版日期: 2008-07-27（万方平台首次上网日期，不代表论文的发表时间）