Presentation 2007-10-26
Color Image Classification Using Block Image Replacement and Local Averaging Classifier(Internationa Session 7)
Kazuki KONDO, Seiji HOTTA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we propose a color image classification method using block image replacement and a local averaging classifier (LAC). First, an input image and training ones are partitioned into block images. The k-nearest blocks of each block of the input image are selected from the blocks of training images in individual classes. Next, each block of the input image is replaced with the mean block computed with its selected k-nearest blocks. Finally, the proposed method outputs the class that has the minimum distance between the block-replaced image and the input one. In the proposed method, the number of blocks tends to be large, so reduction of blocks with modified learning vector quantization is presented in this paper. The performance of the proposed method is verified with experiments on the WANG color image dataset.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) color image classification / block image replacement / local averaging classifier / learning vector quantization
Paper # PRMU2007-121
Date of Issue

Conference Information
Committee PRMU
Conference Date 2007/10/18(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 ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Color Image Classification Using Block Image Replacement and Local Averaging Classifier(Internationa Session 7)
Sub Title (in English)
Keyword(1) color image classification
Keyword(2) block image replacement
Keyword(3) local averaging classifier
Keyword(4) learning vector quantization
1st Author's Name Kazuki KONDO
1st Author's Affiliation Tokyo University of Agriculture and Technology()
2nd Author's Name Seiji HOTTA
2nd Author's Affiliation Tokyo University of Agriculture and Technology
Date 2007-10-26
Paper # PRMU2007-121
Volume (vol) vol.107
Number (no) 281
Page pp.pp.-
#Pages 6
Date of Issue