TEXT DETECTION IN VIDEO BASED ON WAVELET MODULUS MAXIMUM AND 1-SVM

摘要：

Text presented in videos provides important supplemental information for video indexing and retrieval. Many efforts have been made for text detection in videos. In his paper, we propose a method of text detection based on a wavelet modulus maximum module and a 2-step classification module. The 2-step classification module is composed of a cascade classifier and a one-class support vector machine (1-SVM) classifier. Experimental result shows the method here has better precision and lower false detection rate.

关键词： text detection wavelet modulus maximum cascade classifier 1-SVM

作者: Jian-Liang Zhang Ming-Hai Yao Dong-Lian Qi

作者单位: Dept.of Information Engineering,Zhejiang University of Technology,China Dept.of Electrical Engineering,Zhejiang University,China

会议类型: 国际会议

会议名称: 2008年拟人系统国际会议(2008 International Conference on Humanized Systems )(ICHS’08)

会议地点: 北京

会议语种:英文

在线出版日期: 2008-10-18（万方平台首次上网日期，不代表论文的发表时间）