High accuracy handwritten Chinese character recognition using LDA-based compound distances
High accuracy handwritten Chinese character recognition using LDA-based compound distances
复制标题
DOI：
10.1016/j.patcog.2008.04.011
复制
发表时间：
2008-11-01
影响因子：
8
通讯作者：
Liu, Cheng-Lin
中科院分区：
文献类型：
--
作者：
Gao, Tian-Fu;Liu, Cheng-Lin
为了提高手写汉字识别的准确率，提出了一种基于线性判别分析(LDA)的复合距离来区分相似字符。基于LDA的方法是对以前的复合马氏函数(CMF)的扩展，它在一维子空间(判别向量)上计算用于区分两类的互补距离，并将该互补距离与基线二次分类器相结合。我们使用LDA来估计判别向量，以获得更好的区分性，并表明在受限假设下，CMF是基于LDA的方法的特例。当从高维特征空间估计判别向量时，可以获得进一步的改进。我们使用改进的二次判别函数(MQDF)作为基准分类器，在ETL9B和CAS1A数据库上对这些方法进行了实验评估。实验结果表明了基于LDA的方法比CMF方法的优越性，以及高维特征空间判别向量学习的优越性。与MQDF相比，该方法的误码率降低了26%以上。(C)2008爱思唯尔有限公司。保留所有权利。
To improve the accuracy of handwritten Chinese character recognition (HCCR), we propose linear discriminant analysis (LDA)-based compound distances for discriminating similar characters. The LDA-based method is an extension of previous compound Mahalanobis function (CMF), which calculates a complementary distance on a one-dimensional subspace (discriminant vector) for discriminating two classes and combines this complementary distance with a baseline quadratic classifier. We use LDA to estimate the discriminant vector for better discriminability and show that under restrictive assumptions, the CMF is a special case of our LDA-based method. Further improvements can be obtained when the discriminant vector is estimated from higher-dimensional feature spaces. We evaluated the methods in experiments on the ETL9B and CAS1A databases using the modified quadratic discriminant function (MQDF) as baseline classifier. The results demonstrate the superiority of LDA-based method over the CMF and the superiority of discriminant vector learning from high-dimensional feature spaces. Compared to the MQDF, the proposed method reduces the error rates by factors of over 26%. (C) 2008 Elsevier Ltd. All rights reserved.