A NOVEL COLOR-BASED FEATURE EXTRACTION METHOD FOR SVM BASED SKIN SEGMENTATION

Home Page
About
Submit A Journal
Submit A Conference
Submit Paper/Book
- Submit a Preprint
- Submit a Book
Contact

Eskişehir Technical University Journal of Science and Technology A - Applied Sciences Engineering
Volume:21 Special Issue
A NOVEL COLOR-BASED FEATURE EXTRACTION METHOD FOR SVM BASED SKIN SEGMENTATION

A NOVEL COLOR-BASED FEATURE EXTRACTION METHOD FOR SVM BASED SKIN SEGMENTATION

Authors : Mehmet FİDAN, Utku KAYA

Pages : 45-54

Doi:10.18038/estubtda.818577

View : 31 | Download : 7

Publication Date : 2020-11-27

Article Type : Research Paper

Abstract :The colored digital images can be represented in different color spaces. The most used color space is Red-Green-Blue space. However, this space can be transformed to Luminance-Blue Difference-Red Difference space for extraction of light intensity information and Hue-Saturation-Value space. The defined features of color pixels give strong information about whether they belong to a human skin or not. In this paper, a novel color-based feature extraction method is proposed, which use both red, green, blue, luminance, hue and saturation information. The proposed method is applied on an image database consists of various people with diverse age, racial and gender characteristics. The obtained features are used to segment the human skin by using Support-Vector- Machine algorithm and finally the promising performance results are presented comparatively with the most-common methods in the literature.
Keywords : Feature extraction, Image segmentation, Support Vector Machine

ORIGINAL ARTICLE URL

* There may have been changes in the journal, article,conference, book, preprint etc. informations. Therefore, it would be appropriate to follow the information on the official page of the source. The information here is shared for informational purposes. IAD is not responsible for incorrect or missing information.