一种非均匀照明彩色图像自适应校正方法  

An Adaptive Method for Color Image Correction with Non-uniform Illumination

作　　者：李灿林 刘金华 张卫正 刘岩 毕丽华 LI Can-lin;LIU Jin-hua;ZHANG Wei-zheng;LIU Yan;BI Li-hua(College of Computer and Communication Engineering,Zhengzhou University of Light Industry,Zhengzhou 450001,China;Office of Discipline Construction,Zhengzhou University of Light Industry,Zhengzhou 450001,China)

机构地区：[1]郑州轻工业大学计算机与通信工程学院,郑州450001 [2]郑州轻工业大学学科建设办公室,郑州450001

出　　处：《科学技术与工程》2021年第10期4133-4140,共8页Science Technology and Engineering

基　　金：国家自然科学基金(U1404623);河南省科技攻关项目(212102210097)。

摘　　要：为解决非均匀照明条件下彩色图像亮度不均、细节丢失、对比度低等问题,提出一种非均匀照明彩色图像自适应校正方法研究非均匀照明图像的自适应增强。首先,提出一种双伽马校正直方图均衡(bilateral Gamma adjustment histogram equalization, BIGAHE)算法处理HSV颜色空间的V通道,来调整图像全局对比度和亮度,同时使用构建的自适应拉伸函数对S通道进行非线性拉伸以提高图像整体饱和度,然后利用对比度受限的自适应直方图均衡算法(contrast limited adaptive histogram equalization, CLAHE)对L*a*b*颜色空间中L*通道进行局部对比度增强,得到最终增强图像。实验结果表明,与现有流行的图像增强方法相比,该算法的平均梯度(mean gradient, MG)、熵(entropy)指标为所有对比算法中最优,对比度改善指数(contrast improvement index, CII)在所有方法中排名第二。可见该算法能够有效提高非均匀照明图像亮度和对比度,提供更多的细节增强,同时避免过度增强,保持图像的自然性,获得更好的增强效果。To solve the problems of uneven brightness, loss details, and low contrast of color images under non-uniform conditions, an adaptive correction method was proposed for color image with non-uniform illumination, which adaptively enhances the image with non-uniform illumination. The proposed algorithm includes the following steps. First, the bilateral gamma adjustment histogram equalization(BIGAHE) algorithm was proposed to V channel of HSV color space to adjust the global contrast and brightness of the image, and the S channel was stretched nonlinearly to improve the saturation of image by using the constructed adaptive stretching function. Then, the contrast limited adaptive histogram equalization(CLAHE) was used to enhance the local contrast of the image in L* channels of L* a* b* color space. Finally, the enhanced color image could be obtained. The experimental results show that compared to the popular image enhancement methods, the mean gradient(MG) and entropy indicators of the algorithm were the best among all the comparison algorithms. The contrast improvement index(CII) ranks second among all the methods. It was concluded that the proposed algorithm could effectively improve the brightness and contrast of color image with non-uniform illumination, provide more enhancement of details, avoid over-enhancement, maintain the naturalness of the image, and achieve the better enhancement effect.

关 键 词：彩色图像增强 非均匀照明 双伽马校正直方图均衡(BIGAHE)算法 L*a*b*颜色空间 HSV颜色空间 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]