摘要
提出一种基于自动白平衡和多项式回归相结合的图像校正算法.首先采用基于完美反射的白平衡算法对图像色彩进行整体调整,然后以24色标准色卡为参考色,使用多项式回归算法对图像进行色彩校正.实验结果表明,算法优于传统的颜色校正算法,能更好地实现肤色校正.
Human skin color and brightness deviation under different lighting conditions are the main problems faced by digital Chinese medicine diagnosis.Nowadays,common solutions have their own advantages and disadvantages.An image correction algorithm is proposed based on automatic white balance and polynomial regression.The algorithm firstly uses the white balance algorithm based on perfect reflection to adjust the color of the image as a whole,then uses the 24-color standard color card as the reference color,and uses the polynomial regression algorithm to color correct the image.The experimental results show that the proposed algorithm is superior to the traditional color correction algorithm and can better achieve skin color correction.
作者
胡志阳
谭佳源
刘国华
Hu Zhiyang;Tan Jiayuan;Liu Guohua(Tianjin Key Laboratory of Optoelectronic Sensor and Sensing Network Technology,College of Electronic Information Technology and Optical Engineering,Nankai University,Tianjin 300071,China)
出处
《南开大学学报(自然科学版)》
CAS
CSCD
北大核心
2022年第4期25-28,37,共5页
Acta Scientiarum Naturalium Universitatis Nankaiensis
基金
中央高校基本科研业务费专项资金资助。
关键词
中医望诊图像
白平衡
多项式回归
颜色校正
标准色卡
Chinese medicine observation image
white balance
polynomial regression
color correction
standard color checker