Citation link:
Authors:
Муратовски, Красимир; Muratovski, Krasimir; Бумбаров, Огнян Любенов; Boumbarov, Ognian Lyubenov; Щилянова, Диана Йорданова; Shtilyanova, Diana Yordanova
Title:
Сравнение на вероятностни цветни модели за отделяне на области с кожа
Other Titles:
Comparison of probabilistic color models for skin regions detection
Date of Issue:
2008
Is Part of:
Proceedings of the Technical University – Sofia, 58(1), 2008, pp. 108-117
Publisher:
Технически университет - София
Identifiers:
1311-0829 [issn]
Type:
Article
Language:
eng
Abstract:
This paper presents a comparison between the possibilities of two probabilistic models to detect image areas containing human skin. The major sign used during the classification is the probability for any element to contain the color distribution of a human skin. The analyzed two probabilistic models by this paper are two- dimensional histogram and Single Gaussian Model (SGM). Both of these models are representing the color data from the input image in the YCbCr color space, and the results are rated by applying ROC analysis. The results obtained by this research may be applied for face detection in static images and face tracking in video sequences.
Description:
Reviewer prof. PhD Alexander Bekjarski. - Formulas, tables, diagr. - References, pp. 117
