针对传统弹性匹配法在手写字符识别中存在着由于过匹配而造成误识别的不足,提出一种基于高阶统计的形变弹性匹配法。根据高阶统计量包含字符形状上的细节变化信息,采用独立分量分析抽取出每个字符类的内在变化方向,并将其应用到弹性匹配的形变模型中。字符的任意种形状变化由这组独立分量的线性叠加来表示。通过形变模型,类模板字符发生形变逐次向输入待识别字符趋近,从而在两个字符之间求得一种最佳匹配。在实验结果中,识别率达到92.81%,得到了提高,表明该方法的有效性。
Abstract
Aiming at the problem of misrecognitions due to overfitting in conventional elastic matching for handwritten character recognitin, a deformable elastic matching approach based on high order statistics is proposed in this paper. According to the handwriting variations in shape details contained in high order statistics, the intrinsic deformations within each character class are extracted from the actual deformations by independent component analysis. Then they are applied to the deformable model. Thus any deformation of a class can be described by the weighted linear combination of the independent components. In this model the prototype character is deformed gradually in an effort to be much closer to the input character. In experimental results, higher recognition rates are obtained with average rate up to 92.81% , which shows that the proposed approach is very effective for handwritten characters recognition.
关键词
人工智能 /
模式识别 /
手写字符识别 /
高阶统计 /
弹性匹配 /
内在形变 /
独立分量分析(ICA)
{{custom_keyword}} /
Key words
artificial intelligence /
pattern recognition /
handwritten character recognition /
high order statistics /
elastic matching /
intrinsic deformation /
independent component analysis (ICA)
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] S. Uchida and H. Sakoe. Eigen-deformations for elastic matching based handwritten character recognition[J]. Pattern Recognition, 2003, 36 (9) : 2031 - 2040.
[2] 金连文,徐秉铮. 限定性手写汉字识别的一种可变形弹性匹配模型[J]. 电子学报. 1997, 25 (5) : 35 - 38.
[3] S. H. Srinivasan, K. R. Ramakrishnan. The independent components of characters are 'strokes’[A]. In: Proceedings of the Fifth International Conference on Document Analysis and Recognition (ICDAR 1999 ) [C] , 1999: 414 - 417.
[4] S. Uchida. A Survey of elastic matching techniques for handwritten character recognition [J]. IEICE Transactions on Information and Systems, 2005, E88-D (8) : 1781 - 1790.
[5] 杨竹青,李勇,胡德文. 独立成分分析方法综述[J]. 自动化学报. 2002, 28 (5) : 762 - 772.
[6] M. A. Ronee, et al. Handwritten character recognition using piecewise linear two-dimensional warping[A]. In: Proceedings of Sixth International Conference on Document Analysis and Recognition (ICDAR 2001 ) [C] , 2001: 39 - 43.
[7] Hyvarinen A., Oja E. A fast fixed-point algorithm for independent component analysis[J]. Neural Computation, 1997, 9 (7) : 1483 - 1492.
[8] T. Wakahara, Y. Kimura, A. Tomono. Affine-invariant recognition of gray-scale characters using global affine transformation correlation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23 (4) : 384 - 395.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国防基础研究项目基金资助(J1500C002)
{{custom_fund}}
PDF(141 KB)
