Presentation 1996/11/21
Spotting recognition of gestures performed by people from a single time-varying image
Takuichi Nishimura, Toshiro Mukai, Ryuichi Oka,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We have studied spotting recognition of human gestures from time-varying images. In this paper, our purpose is the spotting recognition of gestures performed by people from a single time-varying image. In order to realize such purpose, we propose to use special camera which can capture many people easily, and also new robust feature extraction method which enables the system to recognize small sized people's gestures in the image. Furthermore, we shows the effectiveness of the method by some experiments.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) gesture recognition / motion image processing / continuous DP / spotting / man-machine dialogue
Paper # PRMU96-90
Date of Issue

Conference Information
Committee PRMU
Conference Date 1996/11/21(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 Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Spotting recognition of gestures performed by people from a single time-varying image
Sub Title (in English)
Keyword(1) gesture recognition
Keyword(2) motion image processing
Keyword(3) continuous DP
Keyword(4) spotting
Keyword(5) man-machine dialogue
1st Author's Name Takuichi Nishimura
1st Author's Affiliation Tsukuba Research Center Real World Computing Partnership()
2nd Author's Name Toshiro Mukai
2nd Author's Affiliation Tsukuba Research Center Real World Computing Partnership
3rd Author's Name Ryuichi Oka
3rd Author's Affiliation Tsukuba Research Center Real World Computing Partnership
Date 1996/11/21
Paper # PRMU96-90
Volume (vol) vol.96
Number (no) 384
Page pp.pp.-
#Pages 8
Date of Issue