• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

J4 ›› 2011, Vol. 33 ›› Issue (6): 63-66.doi: 10.3969/j.issn.1007130X.2011.

• 论文 • 上一篇    下一篇

基于分块DCT的视频文字检测算法

刘凌霞1,牛红惠1,崔洲涓2   

  1. (1.安阳师范学院计算机教学部,河南 安阳 455000;
    2.西安理工大学机械与精密仪器工程学院,陕西 西安 710048)
  • 收稿日期:2010-12-01 修回日期:2011-02-26 出版日期:2011-06-25 发布日期:2011-06-25
  • 作者简介:刘凌霞(1977),女,河南安阳人,硕士,讲师,研究方向为图像图形处理和数据挖掘。牛红惠(1972),女,河南濮阳人,硕士,讲师,研究方向为计算机网络、神经网络算法及应用和数据挖掘。崔洲涓(1986),女,河南安阳人,硕士生,研究方向为光通信和FPGA设计。

A Novel DCTBased Video Text Detection Algorithm

LIU Lingxia1,NIU Honghui1,CUI Zhoujuan2   

  1. (1.Computer Education Department,Anyang Normal University,Anyang 455000;
    2.School of Mechanical and Instrumental Engineering,Xi’an University of Technology,Xi’an 710048,China)
  • Received:2010-12-01 Revised:2011-02-26 Online:2011-06-25 Published:2011-06-25

摘要:

针对大量视频图像中出现的各种文字信息,本文提出了一种基于离散余弦变换(DCT)的文字提取算法。该方法首先将图像分割为等大小基本块,然后对各小块提取DCT特征。在此基础上,利用图像对比度,设计了一种动态阈值分割方法,可将文字信息和背景信息进行分离。然后依据最小外接矩形算法,获得初始文字检测结果。最终使用Voronoi Diagram算法对初始区域进行合并得到最终文字区域检测结果。算法可以快速而精确定位文字所对应的区域,并且能适用于各种背景条件下的视频图像。

关键词: 视频图像, 文字识别, 检测, 离散余弦变换, 结构分析

Abstract:

To help users navigate the libraries of video, algorithms that automatically index video based on the content are needed. In this paper, we present a DCT based approach to detect texts and captions from the videos. The use of these features is in a flexible manner thus can be adapted to different applications. Language independence is an important advantage of the proposed method. Experiments are conducted on a large volume of real video shots. Solutions are proposed for each of these problems and compared with the existing work found in the literature.

Key words: video;text recognition;detection;DCT;structural analysis