Image Enhancement Algorithm for Hexagonal Cellular Neural Networks

In this paper, we propose an image enhancement algorithm for a display. Traditionally, high dynamic range algorithms handle the conversion from the scene in the real world to the screen in a display since the optical-physical conditions are changed. Similar reasons motivated our study of analyzing the relationship between the display and the human vision system (HVS). In this paper, we introduce an image enhancement algorithm, which is based on a well-known high-dynamic range compression algorithm, named Retinex theory. Retinex theory provides an approach of separating the illumination from the reflectance in a given image and thereby compensating for nonuniform lighting. The proposing algorithm is implemented on an advance cellular neural network structure, the hexagonal-type cellular neural network (hCNN). Via examining the stable central linear system of a hCNN, we are able to implement the Retinex theory and operate the CNN in the stable region. Meanwhile, we propose an approach to estimate the parameters in the Retinex theory based on the analysis of the interactions between the retina and the display. Those parameters vary depending on the environment and usually are difficult to obtain. Proposing algorithm is based on biological inspired technology. In our experiments, some quite good results are obtained