Proceedings of the Korean Society of Broadcast Engineers Conference (한국방송∙미디어공학회:학술대회논문집)

The Korean Institute of Broadcast and Media Engineers (한국방송∙미디어공학회)
권호 표지

A Chinese Spam Filter Using Keyword and Text-in-Image Features

  • Chen, Ying-Nong (Department of Computer Science and Information Engineering, National Central University) ;
  • Wang, Cheng-Tzu (Department of Computer Science, National Taipei University of Education) ;
  • Lo, Chih-Chung (Department of Informatics, Fo Guang University) ;
  • Han, Chin-Chuan (Department of Computer Science and Information Engineering, National United University) ;
  • Fana, Kuo-Chin (Department of Computer Science and Information Engineering, National Central University)
  • Published : 2009.01.12
Download PDF
⟨ Previous Next ⟩

Abstract

Recently, electronic mail(E-mail) is the most popular communication manner in our society. In such conventional environments, spam increasingly congested in Internet. In this paper, Chinese spam could be effectively detected using text and image features. Using text features, keywords and reference templates in Chinese mails are automatically selected using genetic algorithm(GA). In addition, spam containing a promotion image is also filtered out by detecting the text characters in images. Some experimental results are given to show the effectiveness of our proposed method.

Keywords