基于模糊同质性映射的文本检测方法

黄剑华; 承恒达; 吴锐; 刘家锋

doi:10.3724/SP.J.1146.2006.01757

基于模糊同质性映射的文本检测方法

doi: 10.3724/SP.J.1146.2006.01757

基金项目:

国家自然科学基金(60573071)和国家863计划(2003AA5015 22)资助课题

计量
- 文章访问数: 2898
- HTML全文浏览量: 98
- PDF下载量: 1010
- 被引次数: 0
出版历程
- 收稿日期: 2006-11-09
- 修回日期: 2007-04-27
- 刊出日期: 2008-06-19

A New Approach for Text Detection Using Fuzzy Homogeneity

摘要

摘要: 视频图像中的文本是从语义层次对视频图像内容进行描述的非常有效信息,文本检测为基于语义的图像检索提供了条件。该文提出了一种基于模糊逻辑和同质映射相结合的文本检测方法,首先利用最大信息熵准则将原始图像模糊化;然后构造基于边缘信息和纹理信息的图像同质性,并利用它将图像映射到模糊同质性空间;最后在模糊同质性空间通过纹理分析检测文本区域。与直接在图像空间域中提取特征的文本检测方法相比,该方法对复杂背景视频图像的文本检测取得了更好的效果,并且适用于多种类型的视频图像中文本的检测。
- 文本检测; 模糊逻辑; 同质性; 纹理分析
Abstract: Text data presented in images and video contains useful and important semantic information for semantic-based image retrieval system. In this paper, a method is proposed for text detection based on fuzzy logic and homogeneity. First, the original images is fuzzified based on the maximum entropy principle. Then edge and textural information is extracted to evaluate the homogeneity of image which is transformed to fuzzy homogeneity domain. Finally text region is confirmed with texture analysis in fuzzy homogeneity domain. Experimental results confirm that the proposed method achieves better performance in complex background and is applicable to various kinds of video and images.

HTML全文

参考文献(1)

Jeong Ki-young, Jung Keechul, and Kim Eun-yi, et al..Neural network-based text location for news video indexing.1999 International Conference on Image Processing, Kobe,Japan, 1999, 3: 319-323.[2]Chen Xiang-rong and Zhang Hong-jiang. Text areadetection from video frames. IEEE Pacific Rim Conferenceon Multimedia ： Advances in Multimedia InformationProcessing, Beijing, China, 2001: 222-228.[3]Lienhart Rainer and Wernicke Axel. Localizing andsegmentation text in images and videos[J].IEEE Trans. onCircuits and Systems for Video Technology.2002, 12(4):256-268[4]Ye Qi-xiang, Huang Qing-ming, and Gao Wen, et al.. Fastand robust text detection in image and video frames[J].Imageand Vision Computing.2005, 23(6):565-576[5]Kim Kwang-in, Jung Kee-chul, and Kim Jin-hyung.Texture-based approach for text detection in images usingsupport vector machines and continuously adaptive meanshift algorithm[J].IEEE Trans. on Pattern Analysis andMachine Intelligence.2003, 25(12):1631-1639[6]Hua Xian-sheng, Liu Wen-ying, and Zhang Hong-jiang.Automatic performance evaluation for video text detection.Document Analysis and Recognition 2001, Proceedings, 6thInternational Conference, Seattle, WA, USA, 2001, 9:545-550.[7]张引，潘云鹤. 面向彩色图像和视频的文本提取新方法. 计算机辅助设计与图像学报, 2002, 14(1): 36-40.Zhang Yin and Pan Yun-he. A new approach for textextraction from color image and video. Journal ofComputer-aided Design Computer Graphics, 2002, 14(1):36-40.[8]Jung Keechul, Kim Kwang-in, and Jain Anil K. Textinformation extraction in image and video: A survey. PatternRecognition, 2004, 37(5): 977-997.[9]Cheng H D and Xu H J. A novel fuzzy logic approach tocontrast enhancement[J].Pattern Recognition.2000, 33(5):809-819[10]Ross T J. Fuzzy Logic with Engineering Applications. NewYork, McGraw-Hill, 1995, chapter 12.[11]Pal S K and Majumder D K D. Fuzzy MathematicalApproach to Pattern Recognition, New York, John Wiley,1986: 34-40.[12]Kapur J N, Sahoo P K, and Wong A K C. A new method forgrey level picture thresholding using the entropy of thehistogram[J].Computer Vision, Graphics, and ImageProcessing.1985, 29(3):273-285[13]Lucas S M, Panaretos A, and Sosa L, et al.. ICDAR2003Robust reading competition. 2003, Proceedings, 7thInternational Conference on Document Analysis and Recognition,Edinburgh, Scotland, 2003: 682-687.

施引文献

资源附件(0)

访问统计