Presentation 2008-12-18
Automatic Category Classification of Self-Organizing Maps Using Adaptive Learning
Masahiro TSUKADA, Hirokazu MADOKORO, Kazuhito SATO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper presents a method for automatic category classification using a network system that combine additional learning function of ART-2 (Adaptive Resonance Theory) networks, self-representation characteristic of CPN (Counter Propagation Networks), and local feature descriptors by SIFT (Scale-Invariant Feature Transform). In our method, we are possible unsupervised automatic category classification. Our proposed method consists of three important elements: 1) automatic category labeling by ART networks; 2) visiblize spatial relations between categories by CPN; and 3)produce our original histograms basing on vector quantizing SIFT descriptors. Experiment results that used Caltech-256 Object Category Dataset show that our method can successfully build categories from an unsupervised analysis of images.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) ART-2 / CPN / SOM / SIFT / Automatic category classification
Paper # PRMU2008-148
Date of Issue

Conference Information
Committee PRMU
Conference Date 2008/12/11(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 Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Automatic Category Classification of Self-Organizing Maps Using Adaptive Learning
Sub Title (in English)
Keyword(1) ART-2
Keyword(2) CPN
Keyword(3) SOM
Keyword(4) SIFT
Keyword(5) Automatic category classification
1st Author's Name Masahiro TSUKADA
1st Author's Affiliation Faculty of Systems Science and Technology, Akita Prefectural University()
2nd Author's Name Hirokazu MADOKORO
2nd Author's Affiliation Faculty of Systems Science and Technology, Akita Prefectural University
3rd Author's Name Kazuhito SATO
3rd Author's Affiliation Faculty of Systems Science and Technology, Akita Prefectural University
Date 2008-12-18
Paper # PRMU2008-148
Volume (vol) vol.108
Number (no) 363
Page pp.pp.-
#Pages 6
Date of Issue