Presentation 1996/12/13
Feature Extraction for Facial Images using Fractal-Analysis
Akiko HONDA, Kazunori KOTANI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper describes a method of feature extraction for facial images to extract expressions using fractal-analysis. To extract the features, we proposed a method of a region segmentation by fractal dimension. Which in obtained by covering blanket method. This system can estimate the position of facial parts (such as eyes, nose, mouth) successfully. If the estimated results depend on the lighting conditions, it can estimate exactly using relationship between each facial parts. We try to analyze the shape of estimated facial features using template matching. If the shape change is large such as "laugh" and "yawn", this system can classify facial expressions into each categories. However if the change is subtle such as "sadness" and motion of eyes, it's cannot classify.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) facial images / facial expressions / Fractal-Analysis / region segmentation
Paper # CS96-135
Date of Issue

Conference Information
Committee CS
Conference Date 1996/12/13(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 Communication Systems (CS)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Feature Extraction for Facial Images using Fractal-Analysis
Sub Title (in English)
Keyword(1) facial images
Keyword(2) facial expressions
Keyword(3) Fractal-Analysis
Keyword(4) region segmentation
1st Author's Name Akiko HONDA
1st Author's Affiliation Graduate School of Information Science, Japan Advanced Institute of Science and Technology()
2nd Author's Name Kazunori KOTANI
2nd Author's Affiliation Graduate School of Information Science, Japan Advanced Institute of Science and Technology
Date 1996/12/13
Paper # CS96-135
Volume (vol) vol.96
Number (no) 402
Page pp.pp.-
#Pages 6
Date of Issue