Presentation 2006-07-13
Automatic learning of defect feature in visual inspection
Koichi Ikuta, Ken-ichi Tanaka, Kazuo Kyuma,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The visual inspection of the industrial product copes with defects that have wide variety of features in the shape, size, and strength. Most of the learning algorithms of the recognition system require specific training patterns for learning of the feature extraction filters. However, there are many cases that the recognition tasks don't have specific training patterns. In this paper, we propose a learning algorithm which reconstructs feature extraction filters on the basis of reinforcement signals. The recognition system constructed by the learning algorithm is robust against environmental variation.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Reinforcement signal / Feature extraction / learning algorithm
Paper # IE2006-26,MVE2006-32
Date of Issue

Conference Information
Committee MVE
Conference Date 2006/7/6(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 Media Experience and Virtual Environment (MVE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Automatic learning of defect feature in visual inspection
Sub Title (in English)
Keyword(1) Reinforcement signal
Keyword(2) Feature extraction
Keyword(3) learning algorithm
1st Author's Name Koichi Ikuta
1st Author's Affiliation Advanced Technology R&D Center Mitsubishi Electric Corporation()
2nd Author's Name Ken-ichi Tanaka
2nd Author's Affiliation Advanced Technology R&D Center Mitsubishi Electric Corporation
3rd Author's Name Kazuo Kyuma
3rd Author's Affiliation Advanced Technology R&D Center Mitsubishi Electric Corporation
Date 2006-07-13
Paper # IE2006-26,MVE2006-32
Volume (vol) vol.106
Number (no) 157
Page pp.pp.-
#Pages 5
Date of Issue