Presentation 2005/3/21
Real-time Human Face Recognition by a Rotation and Size Spreading Neural Network
Tsukasa SAKAMOTO, Kakuji OHKI, Hironobu TAKANO, Kiyomi NAKAMURA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Emulating the parietal cortex, a "rotation and size spreading associative neural network" (RS-SAN net) was developed. We extended the original system to the human face recognition system which learned and recollected human face image. We added an inner product and a minimum distance as shape recognition criteria. The human face presented in the arbitrary orientation angle and size was recognized by correction of the rotation and size changes. However, background and clothing parts were manually filled in black. In this system, the face was recognized by off-line processing. In the present study, we extended the original system to the real-time face recognition system which performed the recognition by on-line processing with the human face image taken by a CCD camera. The human face image became to be obtained without the influence of the environmental condition such as clothes and background. By setting the decision threshold of the minimum distace as 0.14, the equal error rate shown as cross point of the false rejection and the false acceptance rates became about 8%.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Face recognition / Inner product・Minimum distance / Real-time recognition
Paper # NC2004-161
Date of Issue

Conference Information
Committee NC
Conference Date 2005/3/21(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 Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Real-time Human Face Recognition by a Rotation and Size Spreading Neural Network
Sub Title (in English)
Keyword(1) Face recognition
Keyword(2) Inner product・Minimum distance
Keyword(3) Real-time recognition
1st Author's Name Tsukasa SAKAMOTO
1st Author's Affiliation Graduate School of Engineering, Toyama Prefectural University()
2nd Author's Name Kakuji OHKI
2nd Author's Affiliation Graduate School of Engineering, Toyama Prefectural University
3rd Author's Name Hironobu TAKANO
3rd Author's Affiliation Graduate School of Engineering, Toyama Prefectural University
4th Author's Name Kiyomi NAKAMURA
4th Author's Affiliation Graduate School of Engineering, Toyama Prefectural University
Date 2005/3/21
Paper # NC2004-161
Volume (vol) vol.104
Number (no) 758
Page pp.pp.-
#Pages 6
Date of Issue