SIGNAL PROCESSING APPROACH TO OPTIMUM PREPROCESSING FOR ON-LINE RECOGNITION OF HANDWRITTEN JAPANESE CHARACTERS.

被引:0
|
作者
Aizawa, Tadashi [1 ]
Nakagawa, Masaki [1 ]
Takahashi, Nobumasa [1 ]
机构
[1] Fuji Xerox Co, Tokyo, Jpn, Fuji Xerox Co, Tokyo, Jpn
关键词
IMAGE PROCESSING - SIGNAL PROCESSING - Digital Techniques;
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Tablet digitizers, they are expected to be used as the input device for handwritten characters and drawings. As the preprocesing for the point coordinate sequence read from a tablet, only empirical methods have been applied. This paper discusses the preprocessing from the viewpoint of signal processing, and a quantitative evaluation was made for the following two points: (1) directional stability of the preprocessed coordinate sequence; and (2) follow-up (fidelity) of the preprocesses point sequence to the original point sequence. A performance superior to the traditional methods was obtaned by using the following four phases; (1) Adaptive sampling, where sharp corners are stresses, while the sampling points are set uniformly for slow pen movement; (2) interpolation, where the point interval is made uniform for fast pen movement; (3) smoothing by the moving-average filter; and (4) thinning to eliminate redundant points.
引用
收藏
页码:51 / 63
相关论文
共 50 条
  • [31] Character-Position-Free On-line Handwritten Japanese Text Recognition
    Liang, Jianjuan
    Zhu, Bilan
    Kumagai, Taro
    Nakagawa, Masaki
    PROCEEDINGS 3RD IAPR ASIAN CONFERENCE ON PATTERN RECOGNITION ACPR 2015, 2015, : 231 - 235
  • [32] Fast classification of handwritten on-line Arabic characters
    Kour, George
    Saabne, Raid
    2014 6TH INTERNATIONAL CONFERENCE OF SOFT COMPUTING AND PATTERN RECOGNITION (SOCPAR), 2014, : 312 - 318
  • [33] Building compact recognizer with recognition rate maintained for on-line handwritten Japanese text recognition
    Gao, Jinfeng
    Zhu, Bilan
    Nakagawa, Masaki
    PATTERN RECOGNITION LETTERS, 2014, 35 : 169 - 177
  • [34] Performance Evaluation of MLP and RBF Feed Forward Neural Network for the Recognition of Off-Line Handwritten Characters.
    Rishi, Rahul
    Choudhary, Amit
    Singh, Ravinder
    Dhaka, Vijaypal Singh
    Ahlawat, Savita
    Rao, Mukta
    SECOND INTERNATIONAL CONFERENCE ON DIGITAL IMAGE PROCESSING, 2010, 7546
  • [35] A formalization of on-line handwritten Japanese text recognition free from line direction constraint
    Nakagawa, M
    Zhu, BL
    Onuma, M
    PROCEEDINGS OF THE 17TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 2, 2004, : 359 - 362
  • [36] On-line character recognition for handwritten Kannada characters using wavelet features and neural classifier
    Kunte, RSR
    Samuel, RDS
    IETE JOURNAL OF RESEARCH, 2000, 46 (05) : 387 - 393
  • [38] On-line recognition handwritten mathematical symbols
    Zhao, XJ
    Liu, XY
    Zheng, SL
    Pan, BC
    Yuan, YT
    PROCEEDINGS OF THE FOURTH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION, VOLS 1 AND 2, 1997, : 645 - 648
  • [39] Recognition of On-line Handwritten Chemical Expressions
    Yang, Jufeng
    Shi, Guangshun
    Wang, Qingren
    Zhang, Yong
    2008 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-8, 2008, : 2360 - 2365
  • [40] Segmentation of on-line handwritten Japanese text using SVM for improving text recognition
    Zhu, BL
    Tokuno, J
    Nakagawa, M
    DOCUMENT ANALYSIS SYSTEMS VII, PROCEEDINGS, 2006, 3872 : 208 - 219