Name
Abstract | ||
|---|---|---|
The color images produced by digital cameras are usually not in conformity with their intrinsic colors. This will seriously affect computer-aided medical facial image analysis because it is on the basis of accurate rendering of color information. To solve that, we propose an optimized color correction scheme for medical facial images based on a comprehensive study in various aspects: color spaces, color patches and color correction algorithms. Firstly, we utilize undistorted facial images to demarcate complexion gamut. Secondly, we choose the whole color patches located inside the range of complexion gamut as our validation samples and select the most crucial color patches from the gamut as our optimized training samples, followed by the optimization criteria. Thirdly, we select an adaptive target device-independent color space for medical facial images color correction task. Finally, we evaluate the performance of three most popular color correction algorithms, and select the most suitable one to build our final regression model. Qualitative and quantitative experimental results show that the proposed scheme is superior to that based on the ColorChecker 24 and performs very closely to the benchmark training error results while only 24 colors are involved. More importantly, the acquisition environment is well-designed with the system color chromatic aberration of 5.3369, which is quite small and hard to improve, but the color difference still can be perceived by human vision. Through our optimized color correction scheme, we succeed in reducing the color chromatic aberration to 1.5898. Furthermore, the corrected facial images are more consistent with the observed colors by human beings. Compared with the previous works, our color correction scheme is characterized by mission dependence and statistical reliability. Besides, the optimized color correction model has low complexity and high accuracy. All of these features make this scheme distinctive from previous color correction methods and effective for medical facial images color correction task. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1007/s13042-017-0773-6 | International Journal of Machine Learning and Cybernetics |
Keywords | Field | DocType |
Color correction, Complexion gamut, Facial images, Regression model | Computer vision,Gamut,Color space,Computer science,Chromatic aberration,ColorChecker,Color correction,Complexion,Artificial intelligence,Rendering (computer graphics),Color difference | Journal |
Volume | Issue | ISSN |
10 | 5 | 1868-808X |
Citations | PageRank | References |
0 | 0.34 | 13 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jinling Niu | 1 | 0 | 0.34 |
| Changbo Zhao | 2 | 3 | 1.40 |
| Guo-Zheng Li | 3 | 368 | 42.62 |