A Fast and Accurate Text Detection Method From Complex Images

摘要：

　　Text in images and videos is of particular interest.In this paper,we propose a fast and accurate method to detect text in color images with complex backgrounds.Firstly,a fast color quantization algorithm is used to convert color images into several image layers,and then a CC-based analysis algorithm is applied d to obtain candidate text regions in each layer.Finally,the candidate text regions are merged to get final text regions.The results on a large number of images demonstrated the effectiveness of the proposed method.

关键词： graph theoritical clustering color quantization connected component

作者: Zhiyun Ren Linlin Huang

作者单位: School of Automation Science and Electrical Engineering, Beihang University, Beijing, China School of Electronics and Information Engineering, Beijing Jiaotong University, Beijing, China

会议类型: 国际会议

会议名称: 2012 IEEE 11th International Conference on Signal Processing (第11届IEEE信号处理国际会议)

会议地点: 北京

会议语种:英文

页码: 1144-1148

在线出版日期: 2012-10-21（万方平台首次上网日期，不代表论文的发表时间）