COMPUTER RECOGNITION OF UNCONSTRAINED HANDWRITTEN NUMERALS

被引:246
作者
SUEN, CY [1 ]
NADAL, C [1 ]
LEGAULT, R [1 ]
MAI, TA [1 ]
LAM, L [1 ]
机构
[1] CONCORDIA UNIV,DEPT COMP SERV,MONTREAL H3G 1M8,QUEBEC,CANADA
基金
加拿大自然科学与工程研究理事会;
关键词
CHARACTER RECOGNITION; OCR; HANDWRITTEN NUMERALS; RECOGNITION ALGORITHMS; MULTIPLE EXPERTS; COMBINATION OF EXPERT DECISIONS;
D O I
10.1109/5.156477
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
In this paper we present four algorithms developed independently by members of our research team specialized in recognition of unconstrained handwritten numerals. All these methods have high recognition rates and are considered experts by our research group. We also present the different ways experimented on for incorporation of these recognition methods into a more powerful system. By combining them we realize that they complement each other in many ways. The resulting multiple-expert system proves that the consensus of these methods tends to compensate for individual weaknesses, while preserving individual strengths. This paper shows that it is possible to reduce the substitution rate to a desired level while maintaining a fairly high recognition rate in the classification of totally unconstrained handwritten ZIP code numerals. Furthermore, if reliability is of the utmost importance, we can avoid substitutions completely (reliability = 100%) and still retain a recognition rate above 90%. In the last part of this paper, we try to compare results given by some of the most effective numeral recognition systems found in the literature.
引用
收藏
页码:1162 / 1180
页数:19
相关论文
共 37 条
  • [1] Ahmed P., 1984, Seventh International Conference on Pattern Recognition (Cat. No. 84CH2046-1), P593
  • [2] AHMED P, 1987, INT J PATTERN RECOGN, V1, P1
  • [3] SYNTACTIC RECOGNITION OF HANDWRITTEN NUMERALS
    ALI, F
    PAVLIDIS, T
    [J]. IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1977, 7 (07): : 537 - 541
  • [4] BATISTA G, 1988, PATTERN RECOGN, V21, P287
  • [5] BEUN M, 1973, PHILIPS TECH REV, V33, P89
  • [6] BEUN M, 1973, PHILIPS TECH REV, V33, P130
  • [7] HANDPRINTED SYMBOL RECOGNITION SYSTEM
    BROWN, RM
    FAY, TH
    WALKER, CL
    [J]. PATTERN RECOGNITION, 1988, 21 (02) : 91 - 118
  • [8] AN ALTERNATE SMOOTHING AND STRIPPING ALGORITHM FOR THINNING DIGITAL BINARY PATTERNS
    CHU, YK
    SUEN, CY
    [J]. SIGNAL PROCESSING, 1986, 11 (03) : 207 - 222
  • [9] Cohen E., 1991, International Journal of Pattern Recognition and Artificial Intelligence, V5, P221, DOI 10.1142/S0218001491000156
  • [10] A COMBINATION OF STATISTICAL AND SYNTACTICAL PATTERN-RECOGNITION APPLIED TO CLASSIFICATION OF UNCONSTRAINED HANDWRITTEN NUMERALS
    DUERR, B
    HAETTICH, W
    TROPF, H
    WINKLER, G
    [J]. PATTERN RECOGNITION, 1980, 12 (03) : 189 - 199