Presentation 1998/11/12
Automatic Construction of Image Transformation Processes based on Evolutionary Optimization of Tree Structure
Shinya Aoki, Tomoharu Nagao,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We previously proposed a method to construct antomatically image transformation processes which consist of a sequence of several known image filters. They are optimized to approximate the transformation from an original image to a target image by means of a genetic algorithm where the target image is an ideally processed image made manually. In this paper, we propose an extended method. We put image filters which have several inputs together into tree structures. And then the constructed processes have several input channels and the outputs of them are composed at any point.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) tree structure / image transformation / automatic construction / evolutionary optimization
Paper # PRMU98-120
Date of Issue

Conference Information
Committee PRMU
Conference Date 1998/11/12(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 Construction of Image Transformation Processes based on Evolutionary Optimization of Tree Structure
Sub Title (in English)
Keyword(1) tree structure
Keyword(2) image transformation
Keyword(3) automatic construction
Keyword(4) evolutionary optimization
1st Author's Name Shinya Aoki
1st Author's Affiliation Imaging Science and Engineering Laboratory, Tokyo Institute of Technology()
2nd Author's Name Tomoharu Nagao
2nd Author's Affiliation Imaging Science and Engineering Laboratory, Tokyo Institute of Technology
Date 1998/11/12
Paper # PRMU98-120
Volume (vol) vol.98
Number (no) 394
Page pp.pp.-
#Pages 8
Date of Issue