Presentation 2002/3/11
Positional Invariant Recognition of Face Shape, Orientation and Size by a FFT Rotation, Size Spreading Neural Network
Kazuya ARIMURA, Maki MURAKAMI, Kiyomi NAKAMURA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We previously proposed a rotation and size spreading associative neural network. The characteristics of this neural net is to spread the information of axis orientation and size of the object on surrounding space by spreading weight that has similar tuning characteristics to axis orientation neurons and size discrimination neurons in the parietal cortex. This neural net recognizes shape, orientation and size simultaneously. But the shift of the object in two-D space was not taken into consideration. In the present study, we examined the recognition characteristics of the rotation and size spreading associative neural network in two-D space. We then developed a FFT rotation, size spreading neural net. The FFT rotation, size spreading neural net recognizes the face shape in all orientation, irrespective of its position in two-D space. This net also recognizes the rotation (ranging from -75 to 75°), and size irrespective of its position in two-D space.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Spreading Layer / Orientation Recognition / Size Recognition / Shape Recognition / Position Invariance
Paper # NC2001-140
Date of Issue

Conference Information
Committee NC
Conference Date 2002/3/11(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) Positional Invariant Recognition of Face Shape, Orientation and Size by a FFT Rotation, Size Spreading Neural Network
Sub Title (in English)
Keyword(1) Spreading Layer
Keyword(2) Orientation Recognition
Keyword(3) Size Recognition
Keyword(4) Shape Recognition
Keyword(5) Position Invariance
1st Author's Name Kazuya ARIMURA
1st Author's Affiliation Graduate School of Engineering Toyama Prefectural University()
2nd Author's Name Maki MURAKAMI
2nd Author's Affiliation Graduate School of Engineering Toyama Prefectural University
3rd Author's Name Kiyomi NAKAMURA
3rd Author's Affiliation Graduate School of Engineering Toyama Prefectural University
Date 2002/3/11
Paper # NC2001-140
Volume (vol) vol.101
Number (no) 735
Page pp.pp.-
#Pages 8
Date of Issue