双通道局部处理的自适应图像增强方法  

Adaptive Image Enhancement via Local Processing in Double Channel

作　　者：窦智[1] 韩玉兵[1] 盛卫星[1] 马晓峰[1] 

机构地区：[1]南京理工大学电子工程与光电技术学院,南京210094

出　　处：《计算机辅助设计与图形学学报》2015年第10期1823-1831,共9页Journal of Computer-Aided Design & Computer Graphics

基　　金：国家自然科学基金(61171165)

摘　　要：为了在无需人工干预的情况下自适应地处理多种不同特征的降质图像,有效恢复图中的细节信息,提出一种双通道局部处理的图像增强方法.首先在HSV色彩空间内分别在亮、暗双通道对亮度分量进行局部分析,计算出与之相适应的增强函数,对图像进行增强;然后对双通道的增强结果进行混合高斯加权合并,得到增强后的亮度分量;最后分析增强前后亮度分布的差异,计算色彩补偿函数,矫正增强过程中引入的色彩失真.此外,还提出一种快速滑窗技术,以有效地降低运算的时间复杂度.实验结果表明,该方法能够灵活地处理如曝光不足、曝光过度、逆光以及雾霾影响等不同种类的图像,甚至是综合了以上多种特性的复杂图像,在处理效果和自适应能力上优势明显.In order to adaptively process various kinds of degraded images and effectively recover their de-tails without manual intervention, an image enhancement algorithm is proposed that locally processes im-ages in double channel. Firstly, in HSV color space, images are analyzed locally to calculate the appropriate enhancement functions in two channels, and then to be enhanced using these functions; then, enhancement results in two channels are weightedly merged using mixed Gaussian functions into enhanced intensity components; finally, a color compensation method is employed that considers intensity transformation to calculate compensation function and correct the color distortion resulting from the enhancement. Further-more, a fast sliding window technique is applied to significantly reduce the computational cost. Experimen-tal results show that the proposed algorithm can flexibly process images with different characteristics such as underexposed, overexposed, backlight, and misty images, as well as complex images of all the mentioned characteristics, the performance and adaptive ability are much better than other methods.

关 键 词：图像处理 对比度增强 局部处理 快速滑窗 多通道增强 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]