Fusion of Multi Color Space for Human Skin RegionSegmentation
Xiang Fan · International Journal of Information and Electronics Engineering · 2013
This paper proposes a technique to extract human skin color regions from the color images based on combination of both RGB and YU'V color spaces. Since skin pixels can vary with ambient light, to find the range of values for which most skin pixels fall in the skin color space becomes a hard task. Therefore, other techniques based on normalized rg, HSV, YUV, YIQ, YCbCr, RGB, YCbCr-YU'V color spaces are presented and compared in this paper in order to select the appropriate control limits for the purpose of skin color segmentation. From the experimental results, the skin detection results obtained by the proposed technique based on RGB-YU'V color model is found to be the most appropriate color model compared to other methods. I. I NTRODUCTION Skin color contains relatively concentrated information in human's faces color images. A skin color detection system is always used in many vision systems, such as gesture recognition, hand tracking, video indexing, region of interest extraction and face detection. The main work of skin color detection is to build a noise filter for removing the non-skin color pixels, so that the remaining skin color pixels will fall in the given color space. A color space is a specification of a coordinate system where each color is represented by a single value. Various color spaces are used for processing digital images. A face detection method based on YCbCr is proposed in (1). In their method, skin color regions are extracted which excludes the non-skin color regions using the sigma control limits for color variations. This skin color detection system is very efficient in accuracy. Apart from this method which utilizes merely one color space, there are also methods which employ more than one color space. Two major methods utilizing more than one color space are based on combination of YCbCr-YU'V and RGB-YU'V color spaces. Both YCbCr-YU'V and RGB-YU'V color spaces are shown to be robust and reliable for human skin color detection. These two approaches are based on saturation parameter control limits. In this paper, a series of skin color segmentation methods based on normalized rg, HSV, YUV, YIQ, YCbCr, RGB,