Presentation 1996/5/17
A Hierarchical Description of Digital Grayscale Images based on Image Dipoles
S. Chinveeraphan, P. Sukanya, R. Takamatsu, M. Sato,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper deals with a hierarchical description of digital grayscale images based on non-local structural features, named image dipoles. An image dipole is defined to be a region whose lines of slope emanate from the same maximum, and reach the same minimum. Incorporating an image dipole based representation of an image into a scale-space filtering, we propose in this paper a hierarchical image dipole description of the image. The proposed description consists of image dipole networks of some scales, and linking of image dipoles across the scales. It will be shown that the description is constructed to contain all local transformations of the image dipole network in the scale-space. That is, any image dipole of the network is at most once morphologically transformed from one scale to another adjacent scale in the description. As an application to computer vision, we demonstrate experiments on face detection to show the usefulness of the description.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) image segmentation / scale-space filtering / hierarchical description / face detection
Paper # PRMU96-22
Date of Issue

Conference Information
Committee PRMU
Conference Date 1996/5/17(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 ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Hierarchical Description of Digital Grayscale Images based on Image Dipoles
Sub Title (in English)
Keyword(1) image segmentation
Keyword(2) scale-space filtering
Keyword(3) hierarchical description
Keyword(4) face detection
1st Author's Name S. Chinveeraphan
1st Author's Affiliation Precision and Intelligence Laboratory Tokyo Institute of Technology()
2nd Author's Name P. Sukanya
2nd Author's Affiliation Precision and Intelligence Laboratory Tokyo Institute of Technology
3rd Author's Name R. Takamatsu
3rd Author's Affiliation Precision and Intelligence Laboratory Tokyo Institute of Technology
4th Author's Name M. Sato
4th Author's Affiliation Precision and Intelligence Laboratory Tokyo Institute of Technology
Date 1996/5/17
Paper # PRMU96-22
Volume (vol) vol.96
Number (no) 41
Page pp.pp.-
#Pages 8
Date of Issue