Summary
the 2014 International Symposium on Nonlinear Theory and its Applications
2014
Session Number:A2L-B
Session:
Number:A2L-B4
Image (Artwork) Retrieval based on Similarity of Touch by Self-Organizing Map with Refractoriness
Kento KADOKURA, Yuko OSANA,
pp.128-131
Publication Date:2014/9/14
Online ISSN:2188-5079
DOI:10.34385/proc.46.A2L-B4
PDF download (886.1KB)
Summary:
In this paper, we propose an image (artwork) retrieval based on touch by self-organizing map with refractoriness. Most of conventional similarity-based (content-based) image retrieval systems deal with only scenery image, landscape photographs and so on. Only a few retrieval systems for artwork (illustration) have been proposed. However, they can not realize the retrieval based on touch of artwork. The proposed system realizes the retrieval based on similarity of touch using the selforganizing map with refractoriness. In this system, the number of colors, color information, outline information and so on are used as the image feature. We carried out computer experiments in the proposed system which stores 500 images and confirmed that the proposed image retrieval system can retrieve artwork whose touch are similar.