Presentation 2007-09-04
Comparative Study of Segmentation in Monochrome Facial Images : Snake Pedals and Template Matching
Carolina RAMIREZ, Claudio PEREZ, Jun OHYA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The snake pedal model is a rather new active contour algorithm used for segmentation in 2D and 3D digital images, and has been employed with good results in medical imaging. However, its use on other typical images, like facial images, has not been studied deeply. In this paper we evaluate the snake pedal model applied to face segmentation, and more specifically, to parameter extraction, i.e., face aspect ratio, face area and position. We compare its results with the ones of a template matching method. Results indicate that the snake pedal model outperforms the template matching model in face area estimation.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Face segmentation / active contours / snake pedal
Paper # PRMU2007-74,HIP2007-83
Date of Issue

Conference Information
Committee PRMU
Conference Date 2007/8/27(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) Comparative Study of Segmentation in Monochrome Facial Images : Snake Pedals and Template Matching
Sub Title (in English)
Keyword(1) Face segmentation
Keyword(2) active contours
Keyword(3) snake pedal
1st Author's Name Carolina RAMIREZ
1st Author's Affiliation Waseda University, GITS()
2nd Author's Name Claudio PEREZ
2nd Author's Affiliation Universidad de Chile
3rd Author's Name Jun OHYA
3rd Author's Affiliation Waseda University, GITS
Date 2007-09-04
Paper # PRMU2007-74,HIP2007-83
Volume (vol) vol.107
Number (no) 206
Page pp.pp.-
#Pages 6
Date of Issue