基于成本函数的对比度优化去雾霾算法

Optimized contrast enhancement for dehazing based on cost function

针对雾霾条件下的模糊图像,提出一种对比度优化去雾霾算法。基于一般情况下雾霾图像对比度较低的特点,通过增强其对比度恢复模糊图像。然而,过度补偿退化的对比度可能会截断像素值,导致信息损失,为此制定一个包括对比度和信息丢失的成本函数,通过最小化该成本函数,该算法更优化地提高了对比度并保存了信息。实验结果表明,该算法有效去除了雾霾。

A dehazing algorithm based on contrast enhancement for hazy images was proposed.Based on the observation that the hazy image exhibits low contrast in general,the hazy image was restored by enhancing its contrast.However,the overcompensation of the degraded contrast might truncate pixel values and caused information loss.Therefore,a cost function consisting of the contrast term and the information loss term was formulated.By minimizing the cost function,the proposed algorithm enhances the contrast and preserves the information optimally.Experimental results show that the proposed algorithm effectively removes haze.