LEARNING IN SYNTACTIC RECOGNITION OF SYMBOLS DRAWN ON A GRAPHIC TABLET

被引:14
作者
BERTHOD, M
MAROY, JP
机构
[1] IRIA-LABORIA
来源
COMPUTER GRAPHICS AND IMAGE PROCESSING | 1979年 / 9卷 / 02期
关键词
D O I
10.1016/0146-664X(79)90055-8
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
This paper deals with on-line recognition of handprinted characters and other common symbols, drawn on a graphic tablet. The system relies on meaningful, morphological features and a syntactic, or structural, approach. The first step, after preprocessing, is the representation of a character by the time sequence of its features. This sequence is extracted by means of a finite automation. The representation is completed, when necessary, by topological relations between features. The system can learn to recognize new symbols during normal use, since it needs very few samples for training. © 1979.
引用
收藏
页码:166 / 182
页数:17
相关论文
共 37 条
  • [31] Simek, Tunis, Handprinting input device for computer systems, IEEE Spectrum, 4, 7, pp. 72-81, (1967)
  • [32] Teitelman, Real time recognition of hand-drawn characters, Proceedings, Fall Joint Computer Conference, pp. 559-575, (1964)
  • [33] Teng, Li, Learning Algorithms for Multi-Class Pattern Classification and Problems Associated with On-Line Handwritten Character Recognition, SPCC Report No. 119, (1969)
  • [34] Tou, Evans, Recognition of handwritten characters by topological feature extraction and multilevel categorization, IEEE Transactions on Computers, 100-121, pp. 776-785, (1972)
  • [35] Tucker, Beurle, A two-step strategy for character recognition using geometrical moments, Proceedings, Second International Joint Conference on Pattern Recognition, pp. 223-225, (1974)
  • [36] Watt, Recognition of handprinted numerals reduced to graph representable form, Proceedings, Second International Joint Conference on Artificial Intelligence, pp. 322-332, (1971)
  • [37] Weaver, On-line character recognition, UIUCDCS-R-74-660, (1974)