Author Login Editor-in-Chief Peer Review Editor Work Office Work

Computer Engineering ›› 2011, Vol. 37 ›› Issue (13): 33-35,39. doi: 10.3969/j.issn.1000-3428.2011.13.009

• Networks and Communications • Previous Articles     Next Articles

Handwriting Identification Based on Magnitude and Relative Phase Information

LI Wen-long  1,2, SHANG Zhao-wei  1, ZHANG Ling-feng  1, WANG Jie  1, HU Sheng-xiong  1   

  1. (1. College of Computer Science, University of Chongqing, Chongqing 400030, China; 2. No.77318 Unit of PLA, Wenshan 663000, China)
  • Received:2010-11-01 Online:2011-07-05 Published:2011-07-05

基于幅度和相对相位信息的笔迹鉴别

李文龙1,2,尚赵伟1,张凌峰1,王 杰1,胡胜雄1   

  1. (1. 重庆大学计算机学院,重庆 400030;2. 中国人民解放军77318部队,云南 文山 663000)
  • 作者简介:李文龙(1979-),男,硕士研究生,主研方向:数字图像处理,模式识别;尚赵伟,副教授;张凌峰、王 杰、胡胜雄, 硕士
  • 基金资助:

    国家自然科学基金资助项目(61003120);中央高校基本科研业务费基金资助项目(CDJXS10182216);重庆市自然科学基金资助项目(CSTC2010BB2217)

Abstract:

In order to improve the accuracy of Chinese off-line handwriting recognition, this paper proposes a method based on magnitude and relative phase information of Pyramidal Dual-tree Directional Filter Bank(PDTDFB). Derived Magnitude Distribution(DMD) and relative phase depicted by Von Mises(VM) distribution and Wrapped Cauchy(WC) distribution model are introduced to reflect the features of image in detail, and Resistor-average(RA) distance is applied. According to the idea of Multiple Attribute Decision Making(MADM), the two kinds of features extracted from magnitude and relative phase are fused in the algorithm. Experimental results show that in comparison to Generalized Gaussian Density(GGD) model with PDTDFB, the accuracy of the method increases by 2.2%.

Key words: Pyramidal Dual-tree Directional Filter Banks(PDTDFB), magnitude, relative phase, handwriting identification, Resistor-average(RA) distance

摘要:

为提高脱线中文手写体笔迹鉴别的正确率,提出一种基于金字塔对偶树方向滤波器组(PDTDFB)变换的幅度和相对相位信息的脱线手写体笔迹鉴别方法。该方法利用导出幅度分布和基于相对相位的VM、WC分布模型得到文本图像更详实的特征表示,采用具有对称性的RA距离,依据多属性决策的思想,实现幅度和相对相位信息的特征融合。实验结果表明,该方法的鉴别正确率相比PDTDFB变换与广义高斯密度模型相结合方法提高了2.2%。

关键词: 金字塔对偶树方向滤波器组, 幅度, 相对相位, 笔迹鉴别, RA距离

CLC Number: