Hybrid classifier based method for similar handwritten Chinese character recognition

被引：0
|
作者：
School of Telecommunication Engineering, Xidian Univ., Xi'an [1 ]
710071, China
不详 [2 ]
710071, China
机构：
[1] School of Telecommunication Engineering, Xidian Univ., Xi'an
[2] State Key Lab. of Integrated Service Networks, Xidian Univ., Xi'an
来源：
Xi'an Dianzi Keji Daxue Xuebao | / 5卷 / 26-32期
关键词：
Classifier; Handwritten Chinese character recognition; Modified quadratic discriminant function (MQDF); Similar character recognition; Support vector machine (SVM);
D O I：
10.3969/j.issn.1001-2400.2015.05.005
中图分类号：
学科分类号：
摘要：
To solve the similar handwritten character recognition problem, a novel scheme is proposed to make better use of the feature's discriminative information. Different from the methods for extracting the extra feature for the similar characters, the Modified Quadratic Discriminant Function (MQDF) is first adopted to classify the feature, then the Support Vector Machine (SVM) is used to discriminate the similar characters without the extra feature. To collect the subset of similar characters, the confusion matrix is employed. A new structure for storing the dictionary of the SVM is also proposed for quickly searching. Experimental results on ETL9B show the superior performance of the proposed scheme to the methods for extracting the extra feature, which proves that the feature contains discriminative information for the similar characters and that the proposed scheme can utilize this information very effectively. ©, 2015, Science Press. All right reserved.
引用
收藏
页码：26 / 32
页数：6
相关论文
共 14 条
  • [1] Liu C.L., Yin F., Wang D.H., Et al., Online and Offline Handwritten Chinese Character Recognition: Benchmarking on New Databases, Pattern Recognition, 46, 1, pp. 155-162, (2013)
  • [2] Tian S., Huang H., Recognition of Similar Chinese Handwriting by Support Vector Machine, Journal of Chinese Information Processing, 14, 3, pp. 37-41, (2000)
  • [3] Feng J., Wang Y., Yang Y., Et al., Recognition of Off-line Similar Handwritten Chinese Characters Based on Multi-class Support Vector Machines Classifier, Computer Engineering and Applications, 40, 27, pp. 200-202, (2004)
  • [4] Zhang D., Ma S., Handwritten Similar Chinese Characters Recognition Based on Combining Statistics with Neural Networks Method, Journal of Chinese Information Processing, 13, 3, pp. 33-39, (1999)
  • [5] Gao T.F., Liu C.L., High Accuracy Handwritten Chinese Character Recognition Using LDA-based Compound Distances, Pattern Recognition, 41, 11, pp. 3442-3451, (2008)
  • [6] Izenman A.J., Linear Discriminant Analysis, pp. 237-280, (2008)
  • [7] Leung K.C., Leung C.H., Recognition of Handwritten Chinese Characters by Critical Region Analysis, Pattern Recognition, 43, 3, pp. 949-961, (2010)
  • [8] Gao X., Wen W., Jin L., A Feature Optimization Method for Similar Handwritten Chinese Character Recognition, Journal of Harbin Engineering University, 33, 7, pp. 887-893, (2012)
  • [9] Wang Y., Liu C., Ding X., Similar Pattern Discriminant Analysis for Improving Chinese Character Recognition Accuracy, Proceedings of 12th International Conference on Analysis and Recognition, pp. 1056-1060, (2013)
  • [10] Kimura F., Takashina K., Tsuruoka S., Et al., Modified Quadratic Discriminant Functions and the Application to Chinese Character Recognition, IEEE Transactions on Pattern Analysis and Machine Intelligence, 1, pp. 149-153, (1987)
12