A Retina Inspired Model for Enhancing Visibility of Hazy Images.
A Retina Inspired Model for Enhancing Visibility of Hazy Images.
复制标题
一种增强模糊图像可见度的视网膜启发模型
DOI：
10.3389/fncom.2015.00151
复制
发表时间：
2015
影响因子：
3.2
通讯作者：
Li YJ
中科院分区：
文献类型：
--
作者：
Zhang XS;Gao SB;Li CY;Li YJ
The mammalian retina seems far smarter than scientists have believed so far. Inspired by the visual processing mechanisms in the retina, from the layer of photoreceptors to the layer of retinal ganglion cells (RGCs), we propose a computational model for haze removal from a single input image, which is an important issue in the field of image enhancement. In particular, the bipolar cells serve to roughly remove the low-frequency of haze, and the amacrine cells modulate the output of cone bipolar cells to compensate the loss of details by increasing the image contrast. Then the RGCs with disinhibitory receptive field surround refine the local haze removal as well as the image detail enhancement. Results on a variety of real-world and synthetic hazy images show that the proposed model yields results comparative to or even better than the state-of-the-art methods, having the advantage of simultaneous dehazing and enhancing of single hazy image with simple and straightforward implementation.
