DocumentCode :
597893
Title :
Beard and mustache segmentation using sparse classifiers on self-quotient images
Author :
Le, T. Hoang Ngan ; Khoa Luu ; Seshadri, K. ; Savvides, Marios
Author_Institution :
Dept. of Electr. & Comput. Eng., Carnegie Mellon Univ., Pittsburgh, PA, USA
fYear :
2012
fDate :
Sept. 30 2012-Oct. 3 2012
Firstpage :
165
Lastpage :
168
Abstract :
In this paper, we propose a novel system for beard and mustache detection and segmentation in challenging facial images. Our system first eliminates illumination artifacts using the self-quotient algorithm. A sparse classifier is then used on these self-quotient images to classify a region as either containing skin or facial hair. We conduct experiments on the MBGC and color FERET databases to demonstrate the effectiveness of our proposed system.
Keywords :
image classification; image segmentation; object detection; visual databases; MBGC database; beard detection; beard segmentation; color FERET database; facial hair; facial image; illumination artifact; mustache detection; mustache segmentation; self-quotient algorithm; self-quotient image; skin; sparse classifier; Databases; Face; Hair; Image color analysis; Image segmentation; Lighting; Skin; Beard/mustache detection; segmentation; self-quotient image; sparse classifier;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Image Processing (ICIP), 2012 19th IEEE International Conference on
Conference_Location :
Orlando, FL
ISSN :
1522-4880
Print_ISBN :
978-1-4673-2534-9
Electronic_ISBN :
1522-4880
Type :
conf
DOI :
10.1109/ICIP.2012.6466821
Filename :
6466821
Link To Document :
بازگشت