Skeletonization of broken handwritten characters

被引:1
|
作者
He, R [1 ]
Yan, H [1 ]
机构
[1] Univ Sydney, Sch Elect & Informat Engn, Sydney, NSW 2006, Australia
关键词
broken character recognition; handwriting recognition; thinning; skeletonization;
D O I
10.1117/1.1315024
中图分类号
O43 [光学];
学科分类号
070207 ; 0803 ;
摘要
We present a method for the extraction of the skeletons of broken handwritten characters. The proposed algorithm is based on a comparison of the directional movement of every segment of a broken character, and on the connection between two points on different boundaries whose direction appears to be contrary. If a segment cannot be connected with another segment with an almost opposite direction, the direction of the segment will be turned at an angle until it connects with another segment. The application of the algorithm smoothes the character and removes small gaps and noise on its boundaries. The noniterative skeletonization process is based on the distances from character pixels to the boundaries. At the intersection, the algorithm will connect two thinned segments that are in a contrary direction and extend the segments that have no proper connecting points. (C) 2000 Society of Photo-Optical Instrumentation Engineers. [S0091-3286(00)01311-8].
引用
收藏
页码:2882 / 2893
页数:12
相关论文
共 50 条
  • [1] NATURAL SKELETONIZATION: NEW APPROACH FOR THE SKELETONIZATION OF HANDWRITTEN CHARACTERS
    Dawoud, Amer
    Kamel, Mohamed
    INTERNATIONAL JOURNAL OF IMAGE AND GRAPHICS, 2005, 5 (02) : 267 - 279
  • [2] Fully Convolutional Network Based Skeletonization for Handwritten Chinese Characters
    Wang, Tie-Qiang
    Liu, Cheng-Lin
    THIRTY-SECOND AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTIETH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / EIGHTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2018, : 2540 - 2547
  • [3] New approach for the skeletonization of handwritten characters in cray-level images
    Dawoud, A
    Kamel, M
    SEVENTH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION, VOLS I AND II, PROCEEDINGS, 2003, : 1233 - 1237
  • [4] Linking Broken Characters in Online Handwritten Chemical Formulas
    Zhao, Lin
    Yan, Hu
    Shi, Guangshun
    Yang, Jufeng
    2009 INTERNATIONAL CONFERENCE ON INTELLIGENT HUMAN-MACHINE SYSTEMS AND CYBERNETICS, VOL 2, PROCEEDINGS, 2009, : 154 - 157
  • [5] An End Detection Algorithm for segmentation of Broken and Touching characters in Handwritten Gurumukhi Word
    Mangla, Parika
    Kaur, Harleen
    2014 3RD INTERNATIONAL CONFERENCE ON RELIABILITY, INFOCOM TECHNOLOGIES AND OPTIMIZATION (ICRITO) (TRENDS AND FUTURE DIRECTIONS), 2014,
  • [6] Recognition of broken and noisy handwritten characters using statistical methods based on a broken-character-mending algorithm
    Cheng, DH
    Yan, H
    OPTICAL ENGINEERING, 1997, 36 (05) : 1465 - 1479
  • [7] SKELETONIZATION OF ARABIC CHARACTERS USING CLUSTERING BASED SKELETONIZATION ALGORITHM (CBSA)
    MAHMOUD, SA
    ABUHAIBA, I
    GREEN, RJ
    PATTERN RECOGNITION, 1991, 24 (05) : 453 - 464
  • [8] VARIABILITY IN HANDWRITTEN CHARACTERS
    WING, AM
    VISIBLE LANGUAGE, 1979, 13 (03) : 283 - 298
  • [9] The shape of handwritten characters
    Chakravarthy, VS
    Kompella, B
    PATTERN RECOGNITION LETTERS, 2003, 24 (12) : 1901 - 1913
  • [10] Individuality of handwritten characters
    Zhang, B
    Srihari, SN
    Lee, S
    SEVENTH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION, VOLS I AND II, PROCEEDINGS, 2003, : 1086 - 1090