自适应同态对数光照补偿

Adaptive logarithm for facial illumination compensation based on homomorphic gomomorphic module

人脸检测有广泛的应用前景,但目前的许多人脸检测算法对光照有一定的要求,过亮过暗偏光图像使检测率急剧下降。提出一种自适应同态对数光照补偿方法,用对数函数作为基函数,使变换后的图像符合人的视觉特点;设置对数函数的平移系数,使变换对各种程度过暗过亮偏光阴影图像都可以进行有效的补偿;引入同态补偿公式来补偿光照的同时增强图像细节,使变换后的图像更清晰。实验结果表明,该方法对过暗过亮的人脸图像都可以进行有效的光照补偿,有助于提高人脸检测率。

Face detection has wide applications. But many of the detection algorithms are sensitive to illumination variation. Detection rates usually drop quickly if the illumination is too bright, too dark, or non-uniform illumination. This paper proposed a adaptive logarithm illumination compensation method based neighbour remediation technique, the method use logarithm function as primary function, therefore it＇ s true of human visual trait; and setup the offset＇ s coefficients of logarithm function to solve the illumination problem in varying degree, thus this method is ability of compensation of all types of iw^ge in varying degrees through adjusting the coefficients; and introduce a remediation technique based neighbour area to reduce illumination influence and enhance image details, so the resource of the image which transformed has been improved. Experimental results show that this method is effective in compensating facial images of over-lighting and over-shading, and it is beneficial to improve the facial detection rate.