Preferred Racial Skin Color Reproduction in an Image based on Race Classification
نویسندگان
چکیده
Preferred skin color reproduction is an important factor for improving the image quality of display devices and systems. Therefore, this article presents a race-selective preferred skin color reproduction method for the case of multiple races in a single image. First, the proposed method detects skin regions using a focus map and skin candidate map. Next, the race of each detected skin region is classified by comparing the Euclidean distance of the average chromaticity for each detected skin region with a database of racial skin colors. Based on this classification, the racial preferred skin color for each detected skin region is then selected from candidate racial preferred skin colors that are predefined in a database generated through an observer’s preference test. Finally, the skin color is reproduced toward the preferred skin color. Experimental results confirm that the proposed method can achieve race-selective preferred skin color reproduction in the case of multiple races in a single image. c © 2015 Society for Imaging Science and Technology. [DOI: 10.2352/J.ImagingSci.Technol.2015.59.2.020504] INTRODUCTION Preference colors are typically determined according to the observer’s preference, and are an important subjective measure for image quality evaluation of display equipment. The preference indicates the degree of satisfaction of the observer and is generally enhanced by reproducing the colors of sky, grass, and skin.1 Among these colors, skin color is one of the main factors in preferred color reproduction, as humans tend to perceive people before anything else in an image based on recognizing the skin color.2,3 Therefore, the skin color needs to be enhanced to become more natural for the viewer. Various skin color reproduction methods have already been studied. Kao proposed color reproduction using a color transformation matrix.4 Sanger modeled the preferred skin color area using an ellipse and proposed three preferred skin color ellipses according to the ethnic groups of Asian, Caucasian, and African.2 Yendrikhovskij proposed the enhancement of perceived naturalness using a comparison between reproduced color and preference colors.5 Kim proposed mapping toward the preferred skin color region using an affine transform.6 Nachlieli proposed sensitive skin color enhancement to correspond to human preferences regarding the appearance of people based on CIELab color
منابع مشابه
Interaction Between Race and Gender and Effect on Implicit Racial Bias Against Blacks
Background and aims: <span style="color: #221e1f; font-family: Optima ...
متن کاملHue constrained matrix optimization for preferred color reproduction
A method for preferred color reproduction with a psychophysical study based upon a real-life scene demonstrated application is presented. A color correction matrix optimization algorithm is first introduced which applies additional hue constraints on top of the CIE delta E magnitude error to emphasize the importance of hue in the subjective quality of color reproduction. An application is imple...
متن کاملComparison between two race/skin color classifications in relation to health-related outcomes in Brazil
BACKGROUND This paper aims to compare the classification of race/skin color based on the discrete categories used by the Demographic Census of the Brazilian Institute of Geography and Statistics (IBGE) and a skin color scale with values ranging from 1 (lighter skin) to 10 (darker skin), examining whether choosing one alternative or the other can influence measures of self-evaluation of health s...
متن کاملPreferred Skin Color Enhancement of Digital Photographic Images
Reproducing skin colors pleasingly is essential for photographic color reproduction. Moving skin colors toward their preferred skin color center improves the skin color preference. Two main factors to successfully enhance skin colors are: a method to detect skin colors effectively and a method to morph skin colors toward a preferred skin color region properly. This paper starts with introducing...
متن کاملModified CLPSO-based fuzzy classification System: Color Image Segmentation
Fuzzy segmentation is an effective way of segmenting out objects in images containing both random noise and varying illumination. In this paper, a modified method based on the Comprehensive Learning Particle Swarm Optimization (CLPSO) is proposed for pixel classification in HSI color space by selecting a fuzzy classification system with minimum number of fuzzy rules and minimum number of incorr...
متن کامل