Detection & Selection of Skin and Skin like Background under Complex Background

Sangita Gudadhe, Priti Subramanium

Abstract: Skin detection is the process of finding skin colored pixels and regions in an image or a video. Skin detection plays an important role in a wide range of image processing applications ranging from face detection, face tracking, gesture analysis, and content-based image retrieval systems and to various human computer interaction domains. Skin color has proven to be a useful and robust cue for face detection, localization and tracking. During skin detection some non-skin pixels are usually detected as skin pixels. It is very difficult in images to select skin areas with complex background. The purposed work is an improved skin detection method that uses color spaces and combines color spaces to detect skin areas. The experimental result can separate skin and non-skin color under complex background.

Keywords: skin detection, color spaces, skin pixel, skin color, images