Presentation 2002/3/8
Object Identification Using Combination of Neural Network and Logistic Function
Koji HOTTA, Akira ASANO, Chie MURAKI, Megu OHTAKI, Mitsuji MUNEYASU, Takao HINAMOTO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Object identification is a statistical method to discriminate whether two images are obtained from an identical category of objects or from two distinct categories, based on feature distances between the images. We apply logistic discrimination analysis and estimate the confidence degree of discrimination. We combine it with the feed-forward neural network to improve the discrimination ability near the discrimination boundary, where the confidence degree of discrimination is low. It is shown that our method exceeds the simple logistic discrimination in the discrimination ability, and exceeds the simple neural network in the computational complexity of learning.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Neural Network / Logistic Function / Probability
Paper # PRMU2001-289
Date of Issue

Conference Information
Committee PRMU
Conference Date 2002/3/8(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) Object Identification Using Combination of Neural Network and Logistic Function
Sub Title (in English)
Keyword(1) Neural Network
Keyword(2) Logistic Function
Keyword(3) Probability
1st Author's Name Koji HOTTA
1st Author's Affiliation Graduate School of Engineering, Hiroshima University()
2nd Author's Name Akira ASANO
2nd Author's Affiliation Faculty of Integrated Arts and Sciences, Hiroshima University
3rd Author's Name Chie MURAKI
3rd Author's Affiliation Faculty if Informatics, Okayama University of Science
4th Author's Name Megu OHTAKI
4th Author's Affiliation Research Institute for Radiation Biology and Medicine, Hiroshima University
5th Author's Name Mitsuji MUNEYASU
5th Author's Affiliation Faculty of Engineering, Kansai University
6th Author's Name Takao HINAMOTO
6th Author's Affiliation Graduate School of Engineering, Hiroshima University
Date 2002/3/8
Paper # PRMU2001-289
Volume (vol) vol.101
Number (no) 713
Page pp.pp.-
#Pages 8
Date of Issue