一种改进的基于DCT压缩域的图像字符定位方法  

An Improved Character-localization Algorithm in DCT-compressed Domain

作　　者：张二虎[1] 张绪进[1] 段敬红[1] 

机构地区：[1]西安理工大学信息科学系,西安710048

出　　处：《计算机工程与应用》2004年第27期97-98,208,共3页Computer Engineering and Applications

摘　　要：提取图像内的文字信息是基于内容的检索的重要内容,通过提取后的文字能够对图像进行快速的浏览与检索,其中快速字符定位是提取图像内的文字信息的关键。论文在文献犤1犦提出的基于DCT压缩域图像字符定位算法的基础上,进一步采用自适应动态阈值及结合块间的信息对原算法进行改进。对比实验结果表明,改进的方法对图像字符定位比原方法准确率更高,漏检情况有一定程度的降低,取得了较好的效果。Extracting character-regions in an image is very important because these characters contain clear clues of retrieving and browsing image from video /image-database efficiently.In this paper,the drawbacks of traditional method in DCT-Compressed Domain presented by Huang in Ref.1are analyzed,and then an improved method is proposed.The method uses the adaptive threshold and the adjacent blocks information to improve the original algorithm.The experimental results show that the correct-localization rate of improved methods is higher than the traditional methods.

关 键 词：字符定位 DCT变换 压缩域处理 形态滤波 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]