基于CLAHE和图像分解的去雾方法

Single image dehazing method based on CLAHE and image decomposition

针对雾天条件下拍摄到的图像对比度低、细节模糊以及颜色暗淡的现象,提出一种基于CLAHE和图像分解的去雾方法。首先,采用限制对比度直方图均衡化(limited contrast histogram equalization,CLAHE)对有雾图像进行增强,有效地提升图像的对比度;然后,在照明—反射模型的基础上,根据照射分量与反射分量的不同特征对增强后的图像进行梯度滤波,将图像进行分解,获得最终包含图像所有细节的反射图像;最后,对反射图像进行Gamma变换,提升图像的亮度,获得最终的去雾图像。利用信息熵、空间频率、平均梯度和运算时间等客观评价标准,与带色彩恢复多尺度Retinex算法(MSRCR算法)和基于暗通道先验去雾算法(He算法)进行对比。实验结果的主观评价和客观评价表明,在雾天图像细节增强和色彩保持方面,本文方法比MSRCR算法和He算法具有更好的效果。

To solve the problems of low contrast, fuzzy and dim color of the images under haze con-ditions, a new method based on CLAHE and image decomposition is proposed. At first, the foggy image is enhanced by limiting the contrast histogram equalization. Then based on the illumination-reflection model, several gradient filters are used for the enhanced image through the different fea-tures between illumination component and reflection component. And the image is decomposed to obtain the reflection image which contains all the details of the image. Finally, a Gamma transform is used for improving the brightness of the reflection component,and get the final fog eliminated im-age. At the same time, the information entropy, spatial frequency, average gradient and operation time of the objective evaluation criteria are compared with the multi-scale Retinex color restoration algorithm and the dark channel prior to fog eliminating algorithm. The subjective evaluation and ob-jective evaluation of the experimental results show that this method is better than the MSRCR algo-rithm and He’s algorithm in the fog image enhancement and color retention.