Presentation 1995/9/28
A Study on Applicability of Genetic Algorithm to Character Image Generation
Hitoshi Sakano, Hiromi Kida, Naoki Mukawa,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We have investigated the nature of feature extractor by visualizing the feature vectors using Genetic Algorithm (GA). So far we succeeded in visualizing reference vectors of character categories and the boundaries between them as character images. In this paper, we discuss GA's applicability to one-to-many mapping, where GA is to solve multimodal optimization problem. To see this, we investigate influences of GA parameters, such as mutation rate and population size, on the character image generation ability in the case of simple mesh feature extractor.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) character recognition / image reconstruction / genetic algorithm / Sharing
Paper # PRU95-118
Date of Issue

Conference Information
Committee PRU
Conference Date 1995/9/28(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 Understanding (PRU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Study on Applicability of Genetic Algorithm to Character Image Generation
Sub Title (in English)
Keyword(1) character recognition
Keyword(2) image reconstruction
Keyword(3) genetic algorithm
Keyword(4) Sharing
1st Author's Name Hitoshi Sakano
1st Author's Affiliation NTT DATA COMMUNICATIONS SYSTEMS CORPORATION Laboratories for Information Technology()
2nd Author's Name Hiromi Kida
2nd Author's Affiliation Multi Media technology Center
3rd Author's Name Naoki Mukawa
3rd Author's Affiliation NTT DATA COMMUNICATIONS SYSTEMS CORPORATION Laboratories for Information Technology
Date 1995/9/28
Paper # PRU95-118
Volume (vol) vol.95
Number (no) 278
Page pp.pp.-
#Pages 6
Date of Issue