Skip to main navigation Skip to search Skip to main content

A greedy clustering algorithm along the time axis for Chinese language recognition

  • Jiangqin Wu*
  • , Wen Gao
  • , Jingkai Liang
  • , Xiangqian Wu
  • *Corresponding author for this work
  • Harbin Institute of Technology

Research output: Contribution to journalConference articlepeer-review

Abstract

Sign language is the language used by the deaf. Chinese Sign Language(CSL) is primarily composed of gesture language, complemented by finger-spelling language, containing 30 finger-spelling alphabets and about 5500 basic sign words. This paper focuses on CSL recognition. According to the characteristics of sign word of gesture language for CSL, a greedy clustering algorithm along the time axis(GLATA) is proposed to segment sign word, a training algorithm based on GLATA is proposed to train the template corresponding to each word, and a recognizing algorithm based on GLATA is used to recognize 227 words randomly selected from CSL with the accuracy of 96%. In addition, sign segmentation technique based on overall movement speed of hand is proposed to delete "Movement Epenthesis" in continuous sign language. From experiment result, it is shown that GLATA is an effective algorithm for CSL recognition.

Original languageEnglish
Pages (from-to)2439-2444
Number of pages6
JournalProceedings of the IEEE International Conference on Systems, Man and Cybernetics
Volume4
StatePublished - 2001
Event2001 IEEE International Conference on Systems, Man and Cybernetics - Tucson, AZ, United States
Duration: 7 Oct 200110 Oct 2001

Keywords

  • A greedy clustering algorithm along the time axis
  • Chinese sign language
  • Gesture language
  • Sign language recognition

Fingerprint

Dive into the research topics of 'A greedy clustering algorithm along the time axis for Chinese language recognition'. Together they form a unique fingerprint.

Cite this