Presentation 2002/9/12
Recognition of Global Motion in Sign Language Based on Optical Flow
Yuji OKAZAWA, Yasuo HORIUCHI, Akira ICHIKAWA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Sign language is a complicated visual language expressed by various body organs and can be used in real time dialogue. In previous researches, it was shown that human signers can recognize signs to some extent using only global features. In this study, we introduce a recognition method of global motion of hands in sign language based on optical flow. First, we made two-dimensional pattern in which each pixel has the angle of the optical flow vector calculated from videotape. Second, some features are extracted from the pattern by domain unification based on each pixel value. Finally, we performed DP matching algorithm for the features in order to recognize motions. As a result, we got 91.3 percent of recognition rate.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Sign Language / Global Motion of Hands / Optical Flow
Paper # WIT2002-20
Date of Issue

Conference Information
Committee WIT
Conference Date 2002/9/12(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Well-being Information Technology(WIT)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Recognition of Global Motion in Sign Language Based on Optical Flow
Sub Title (in English)
Keyword(1) Sign Language
Keyword(2) Global Motion of Hands
Keyword(3) Optical Flow
1st Author's Name Yuji OKAZAWA
1st Author's Affiliation Graduate School of Science and Technology, Chiba University()
2nd Author's Name Yasuo HORIUCHI
2nd Author's Affiliation Graduate School of Science and Technology, Chiba University
3rd Author's Name Akira ICHIKAWA
3rd Author's Affiliation Graduate School of Science and Technology, Chiba University
Date 2002/9/12
Paper # WIT2002-20
Volume (vol) vol.102
Number (no) 319
Page pp.pp.-
#Pages 6
Date of Issue