Analyzing center/surround retinex

The receptive fields in the Human Visual System (HVS) are organized in such a way that they not merely capture information on the photoreceptor's exposition to light but also on the differences in firing rates of their center and surround cells. This organization can be related with the human's ability to cope with the high dynamic range of natural scenes. As a way to mimic this behavior E. Land proposed in 1986 a perception model consisting in two steps, namely, a local adaptation followed by a global transform. This model gave rise to the so-called Center/Surround tone-mapping algorithms, which are used to map the intensity values of high dynamic range (HDR) images to the limited range of displayable images (typically using 8-bits per channel). In this paper we unify the different Center/Surround algorithms proposed in the literature using a common framework and analyze several possibilities for the local and global operations involved. We accompany our study with quantitative and qualitative results that permit us to suggest the best pair of local/global transforms for a Center/Surround method.