一种强鲁棒性的实时图像增强算法

Highly Robust Real-Time Image Enhancement

提出了一种模拟人类视觉系统的自动图像增强算法.它依据输入图像的统计特征,将全局压缩和局部处理相结合,并且进行了适当的颜色补偿.结果表明,此方法在细节上和速度上都优于传统的Retinex方法,能够快速有效地增强图像质量,适用于包括高对比度低可见度在内的复杂图像,具有实时性和强鲁棒性.

A novel approach which models global and local adaptation of the human visual system （HVS） is developed to automatically render high dynamic range images. This method combines global compression and local processing together, and adopts suitable color restoration. The results show that the method effectively enhances the image qualities and is robust enough to all kinds of images, including complex scenes with highly varying luminance.