Presentation 1998/2/19
Adaptive Divided K-means Algorithm for Image Impression Anarisys
Atsushi KASAO, Masayuki NAKAJIMA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Generally speaking, There are some relations between a composition and a color scheme of an image (i. e. a photograph and a picture) and the impressions the image gives persons. The purpose of our research is to calculate the impression which An image gives persons. Before the calculation, to group the pixel having similar colors and near positions together for simplification is necessary. We have already proposed the new segmentation algorithm to change the shapes along to the direction of texture. However, this algorithm is not enough to take more characteristics relating to impression from an image. In this paper, we propose the expanded algorithm to take more characteristics. And then, we show these characteristics make it possible to find edge areas and directional texture areas as important information to analyze an impression.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) image processing / K-mean's clustering algorithm / texture / directionality / edge / impression analysis
Paper #
Date of Issue

Conference Information
Committee PRMU
Conference Date 1998/2/19(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) Adaptive Divided K-means Algorithm for Image Impression Anarisys
Sub Title (in English)
Keyword(1) image processing
Keyword(2) K-mean's clustering algorithm
Keyword(3) texture
Keyword(4) directionality
Keyword(5) edge
Keyword(6) impression analysis
1st Author's Name Atsushi KASAO
1st Author's Affiliation Tokyo Institute of Technology, Graduate School of Information Science and Engineering()
2nd Author's Name Masayuki NAKAJIMA
2nd Author's Affiliation Tokyo Institute of Technology, Graduate School of Information Science and Engineering
Date 1998/2/19
Paper #
Volume (vol) vol.97
Number (no) 558
Page pp.pp.-
#Pages 8
Date of Issue