Share Email Print

Proceedings Paper

A new color space to discriminate skin regions using fuzzy quadratic programming
Author(s): Amir Mazaherie; Saeed Mirghasemi; Mojtaba Lotfizad
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

This paper presents a new color space through linear conversion in which the cost function has fuzzy quadratic (FQ) characteristic. Training samples are used to create an efficient color space with respect to desired application. Quadratic Programming (QP) technique is engaged to extract the conversion matrix. According to fuzzy feature of the cost function, several matrices are introduced to generate the new color space for skin segmentation. The proposed method involves two steps. First a second order cost function established based on separating target pixels from non-target ones while followed by some constraints. In the second stage, a quadratic optimization is used to solve problem efficiently. Finally, the results of fuzzy approach are compared to non-fuzzy methods.

Paper Details

Date Published: 1 October 2011
PDF: 7 pages
Proc. SPIE 8285, International Conference on Graphic and Image Processing (ICGIP 2011), 82853R (1 October 2011); doi: 10.1117/12.914447
Show Author Affiliations
Amir Mazaherie, Tarbiat Modares Univ. (Iran, Islamic Republic of)
Saeed Mirghasemi, Islamic Azad Univ. (Iran, Islamic Republic of)
Mojtaba Lotfizad, Islamic Azad Univ. (Iran, Islamic Republic of)

Published in SPIE Proceedings Vol. 8285:
International Conference on Graphic and Image Processing (ICGIP 2011)
Yi Xie; Yanjun Zheng, Editor(s)

© SPIE. Terms of Use
Back to Top