Presentation 2001/1/24
A New Method of Flexible Image Retrieval focusing on Global Aspect of Images
Takahiro MOCHIZUKI, Takayuki ITO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The rapid increase in the volume of electoronically archived image and video materials has given rise to needs for new methods of image retrieval, therefore, various approaches have been proposed. Most of conventional image retrieval methods are based on the contents of objects or the features describing the only partial properties of images. But the diversification of images we must deal with has induced the necessity to retrieve images more flexibly and effectively focusing on global aspect of images. In this paper, we propose a new method of flexible image retrieval based on the following two new ideas. One is adopting the fractal vector prospected to include the global information of texture and to relate the one's first impression to an image. The Other is the acquisition extended structural information of images by allowing the rectangular regions, which are set in order to extracting features in multiple points on the image, to be located at slightly various position dependent on image features. Additionally, we show with the results of some experiments on image retrieval that more flexible retrieval can be acheived due to application of the new method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) image retrieval / textural feature / fractal / Active Net
Paper # EID2000-300,IE2000-155
Date of Issue

Conference Information
Committee EID
Conference Date 2001/1/24(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 Electronic Information Displays (EID)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A New Method of Flexible Image Retrieval focusing on Global Aspect of Images
Sub Title (in English)
Keyword(1) image retrieval
Keyword(2) textural feature
Keyword(3) fractal
Keyword(4) Active Net
1st Author's Name Takahiro MOCHIZUKI
1st Author's Affiliation NHK(Japan Broadcasting Corporation) Science and Technical Research Laboratories()
2nd Author's Name Takayuki ITO
2nd Author's Affiliation NHK(Japan Broadcasting Corporation) Science and Technical Research Laboratories
Date 2001/1/24
Paper # EID2000-300,IE2000-155
Volume (vol) vol.100
Number (no) 605
Page pp.pp.-
#Pages 6
Date of Issue