Video text recognition using category-dependent feature extraction based on feature compensation
Video text recognition using category-dependent feature extraction based on feature compensation
复制标题
使用基于特征补偿的类别相关特征提取的视频文本识别
DOI：
10.1002/scj.20361
复制
发表时间：
2005
期刊：
影响因子：
--
通讯作者：
N. Hagita
中科院分区：
文献类型：
--
作者：
M. Mori;M. Sawaki;N. Hagita
当识别多个字体时，诸如笔划的方向信息的几何特征通常对变形是鲁棒的，但对退化是弱的。本文描述了一种类别相关的特征提取方法，使用特征补偿来克服这个弱点。我们提出的方法估计输入模式的退化程度，通过比较输入模式的每个类别的模板。这种估计使我们能够抵消特征值的退化。我们应用所提出的方法识别视频文本遭受退化和变形。对视频中提取的字符进行识别实验，结果表明，该方法在抗退化方面上级传统方法。© 2005 Wiley Periodicals，Inc. Syst Comp Jpn，36（10）：1-8，2005;在线发表于Wiley InterScience（www.interscience. wiley.com）。DOI 10.1002/scj.20361
When recognizing multiple fonts, geometric features, such as the directional information of strokes, are generally robust against deformation but are weak against degradation. This paper describes a category‐dependent feature extraction method that uses feature compensation to overcome this weakness. Our proposed method estimates the degree of degradation of an input pattern by comparing the input pattern to a template of each category. This estimation enables us to offset the degradation in feature values. We apply the proposed method to the recognition of video text suffering from both degradation and deformation. Recognition experiments using characters extracted from videos show that the proposed method is superior to the conventional alternatives in resisting degradation. © 2005 Wiley Periodicals, Inc. Syst Comp Jpn, 36(10): 1–8, 2005; Published online in Wiley InterScience (www.interscience. wiley.com). DOI 10.1002/scj.20361