Paper Info
Title
A Novel Color Correction Framework for Facial Images
Abstract
The color images produced by digital cameras are usually not in conformity with their inherent colors. This will seriously impact computer-aided facial image analysis because it is on the basis of accurate rendering of color information. To solve that, we propose a novel color correction framework. Firstly, we utilize 122 undistorted facial images to demarcate complexion gamut. Secondly, several training sets based on complexion gamut are compared experimentally for the selection of optimal training samples. Thirdly, we select an adaptive target device-independent color space for our facial images color correction task. Finally, we evaluate the performance of three most popular color correction algorithms in color science area, and select the most suitable one to build our final regression model. Compared with the previous work, our color correction framework is characterized by mission dependence and statistical reliability. Besides, its trained model has low complexity and high accuracy. All of these features make it effective for facial images color correction.
Year
DOI
Venue
2014
10.1109/ICMB.2014.16
ICMB
Keywords
DocType
Citations 
facial image color correction task,optimal training sample selection,CCD image sensors,color information,novel color correction framework,color science area,digital cameras,face recognition,undistorted facial images,facial images,regression analysis,complexion gamut,adaptive target device-independent color space,regression model,computer-aided facial image analysis,image sampling,color correction algorithms,statistical reliability,color correction,final regression model,optimal training samples,medical image processing,image colour analysis
Conference
0
PageRank 
References 
Authors
0.34
0
3
Name
Order
Citations
PageRank
Jin-Ling Niu100.34
Chang-Bo Zhao200.34
Guo-Zheng Li336842.62