Comparative Study of Skin Color Detection and Segmentation in HSV and YCbCr Color Space

Abstract

This paper presented a comparative study of human skin color detection HSV and YCbCr color space. Skin color detection is the process of separation between skin and non-skin pixels. It is difficult to develop uniform method for the segmentation or detection of human skin detection because the color tone of human skin is drastically varied for people from one region to another. Literature survey shows that there is a variety of color space is applied for the skin color detection. RGB color space is not preferred for color based detection and color analysis because of mixing of color (chrominance) and intensity (luminance) information and its non uniform characteristics. Luminance and Hue based approaches discriminate color and intensity information even under uneven illumination conditions. Experimental result shows the efficiency of YCbCr color space for the segmentation and detection of skin color in color images.

Human Skin Detection Using RGB, HSV and YCbCr Color Models

“…In region-based skin detection technique, spatial relationship of pixels is considered to define some area from given image as skin region. Initial skin region is grown bigger by adding more pixels based on its neighbors properties [6]. Using machine learning based on available data sets, a classifier can be trained to differentiate the image pixel by pixel (a skin pixel from a non-skin pixel).…”

Using of Color Model and Contrast Variation in Wavelet Ideology for Study <i>Megaloblastic Anemia Cells</i>

“…This is confirmed by the existence of a number of articles [26] [27] [28] [29] [30]. At the same time the HSV color system is preferable in implementing the contrast change procedure.…”

Azure-Based Smart Monitoring System for Anemia-Like Pallor

“…Also, Frangi-superimposed hue (I F hue ) and saturation (I F sat ) color planes result in the maximum classification accuracy. It is noteworthy that covariance/correlation analysis of the 54 features, extracted using model M1, with the output class labels, also demonstrate that Frangi-filtered features [20] and hue, saturation, intensity planes [16,17] have the highest correlation indices.…”

“…Although facial detection and recognition tasks have been well researched since 1960s [15], automated facial recognition tasks continue to face challenges related to the lack of generalizability owing to gender, ethnicity, age and facial occlusions. Among recent noteworthy efforts, the work in [16] demonstrates the usefulness of luminance and hue-based color planes over red-green-blue (RGB) color planes for skin color identification tasks under non-uniform illumination conditions. Another work in [17] uses fuzzy entropy-based approach for representation of skin-tone colors towards facial detection tasks.…”