基于边缘信息和局部直方图的视频文字检测法

作者：郑翠翠，王兴起 日期：2009-11-16/span> 浏览：3006 查看PDF文档

基于边缘信息和局部直方图的视频文字检测法

郑翠翠，王兴起
(杭州电子科技大学 计算机学院,浙江 杭州 310018)

摘要：视频中的标题文字通常在视频信息索引和检索中起到重要的作用。针对视频中文本的检测问题，提出了一种基于边缘和局部直方图的由粗到精的视频标题文字检测算法，首先采用边缘聚集提取文字的粗略位置，然后利用局部直方图特征对候选的文字区域精确定位。实验结果表明，该方法简单，效果良好，能快速地定位文本区域，且不受文本颜色、语种、文本字体大小的限制。
关键词：文本检测;边缘检测;局部直方图
中图分类号：TP391.41文献标识码：A文章编号：1001-4551(2009)10-0031-04

An algorithm for text detection based on edge detection and VGH
ZHENG Cuicui, WANG Xingqi
(School of Computer Science, Hangzhou Dianzi University, Hangzhou 310018, China)
Abstract: Text in video can play an important role in indexing and retrieving semantic information. Aiming at realizing fast and robust text detecting,an algorithm based on edge detection and variant grayscale histogram(VGH) was presented and the coarsetofine localization scheme was used. First, the rough text areas were gotten by edge detection, then the VGH was used to identify text regions accurately. Experimental results on a large number of video images show that the algorithm is effective and simple, the algorithm can detect text regions regardless of colour, language, font style, font size.
Key words: text detecting; edge detection; variant grayscale histogram(VGH)
参考文献(References):
［1］KEECHUL J, ANIL K J. Text information extraction in images and video: a survey［J］. Pattern Recognition,2004,37(5):977-997.
［2］YE Qixiang, HUANG Qingming. Fast and robust text detection in images and video frames［J］. Image and Vision Computing,2005,23(6):565-576.
［3］庄越挺，刘骏伟，吴飞，等.基于支持向量机的视频字幕自动定位与提取［J］.计算机辅助设计与图形学学报，2002,14(8)：750-753.
［4］SONG Yan, LIU Anan, PANG Lin, et al. A Novel Image Text Extraction Method Based on Kmeans Clustering［C］//Computer and Information Science, 2008(ICIS 08). Paris: ［s.n.］,2008:185-190.
［5］LYU M R, SONG Jiqiang, CAI Min. A comprehensive method for multilingual video text detection, localization, and extraction［J］. IEEE Transactions on Circuits and Systems for Video Technology,2005,15(2):243-255.
［6］密聪杰,刘洋,薛向阳.基于多帧图像的视频文字跟踪和分割算法［J］.计算机研究与发展,2006,43(9):1523-1529.
［7］SMITH S M, BRADY J M. SUSANa new approach to low level image processing［J］. Int. Jour. of Computer Vision,1997,23(1):45-78.
［8］LIU Qifeng, JUNG C, KIM S, et al. Stroke Filter for Text Localization in Video Images［C］//IEEE International Conference on Image Processing. Atlanta: ［s.n.］,2006:1473-1476.
［9］张佑生,彭青松,汪荣贵.一种基于变异灰度直方图的视频字幕检测定位方法［J］.电子学报,2004,32(2):314-317.
［10］杨光宇，佟鑫新，朱丹.一种基于FPGA的实时植方图设计方法［J］.机电工程，2007，24（4）：67-69.