Presentation 2004/12/9
Fast Face Detection System by Image Segmentation : Reduction in the search area by adoption of the saliency among clusters
Motofumi FUKUI, Noriji KATO, Hirotsugu KASHIMURA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we introduce a new technique to detect a target object quickly. Our idea is based on remarking on the clusters constructed by image segmentation. By means of calculating the feature value of each cluster and the salience value of it against the peripheral clusters, additionally we eliminate the clusters from the search area which do not resemble a desired target and have a low salience value. We focus on the face detection to evaluate our method, by using our face detection system after restricting the search area. We show that the detection time can be reduced by more than 35% without reducing the detection rate, compared with scanning over the whole image(from 1400ms to 800ms).
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Image Processing / Face Detection / Image Segmentation / K-means Method / Saliency / Color Processing / Visual Processing
Paper # HIP2004-69
Date of Issue

Conference Information
Committee HIP
Conference Date 2004/12/9(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 Human Information Processing (HIP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Fast Face Detection System by Image Segmentation : Reduction in the search area by adoption of the saliency among clusters
Sub Title (in English)
Keyword(1) Image Processing
Keyword(2) Face Detection
Keyword(3) Image Segmentation
Keyword(4) K-means Method
Keyword(5) Saliency
Keyword(6) Color Processing
Keyword(7) Visual Processing
1st Author's Name Motofumi FUKUI
1st Author's Affiliation Corporate Research Lab., Fuji Xerox Co., Ltd.()
2nd Author's Name Noriji KATO
2nd Author's Affiliation Corporate Research Lab., Fuji Xerox Co., Ltd.
3rd Author's Name Hirotsugu KASHIMURA
3rd Author's Affiliation Corporate Research Lab., Fuji Xerox Co., Ltd.
Date 2004/12/9
Paper # HIP2004-69
Volume (vol) vol.104
Number (no) 525
Page pp.pp.-
#Pages 6
Date of Issue