A multi-class pattern recognition system for practical finger spelling translation

被引：27

作者：

Hernandez-Rebollar, JL ^{[1
]}

Lindeman, RW ^{[1
]}

Kyriakopoulos, N ^{[1
]}

机构：

[1] George Washington Univ, Dept ECE, Washington, DC 20052 USA

来源：

FOURTH IEEE INTERNATIONAL CONFERENCE ON MULTIMODAL INTERFACES, PROCEEDINGS | 2002年

关键词：

D O I：

10.1109/ICMI.2002.1166990

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper presents a portable system and method for recognizing the 26 hand shapes of the American Sign Language alphabet, using a novel glove-like device. Two additional signs, 'space', and 'enter' are added to the alphabet to allow the user to form words or phrases and send them to a speech synthesizer. Since the hand shape for a letter varies from one signer to another, this is a 28-class pattern recognition system. A three-level hierarchical classifier divides the problem into "dispatchers" and "recognizers." After reducing pattern dimension from ten to three, the projection of class distributions onto horizontal planes makes it possible to apply simple linear discrimination in 21), and Bayes' Rule in those cases where classes had features with overlapped distributions. Twenty-one out of 26 letters were recognized with 100% accuracy; the worst case, letter U, achieved 78%.

引用

页码：185 / 190

页数：6

共 24 条

[1] [Anonymous], STUDIES LINGUISTICS
[2] BRYSON S, 1993, SIGGRAPH COURSE NOTE, V43
[3] Erenshteyn R., 1999, Proceedings 10th International Conference on Image Analysis and Processing, P229, DOI 10.1109/ICIAP.1999.797600
[4] FUKUMOTO M, C COMP CHI 94, P81
[5] Grimes G. J., 1983, U.S. Patent, Patent No. [4 414 537, 4414537]
[6] HERNANDEZ J, 2002, ACM SIGGRAPH, P259, DOI DOI 10.1145/1242073.1242272
[7] KADOUS MW, 1995, THESIS U NEW S WALES
[8] KESSLER, 1995, ACM T COMPUT-HUM INT, V2, P263
[9] Kramer J., 1988, ACM SIGCAPH COMPUT P, V39, P12, DOI DOI 10.1145/47937.47938
[10] LAMAR MV, 1999, P INT JOINT C NEUR N, V4, P2839

← 1 2 3 →