Abstract: The traditional Retinex algorithm always products “halo” effect in fog and haze image enhancement,and has several shortcomings,such as the poor image exposure,image sharpness,image details,image fidelity and so on.In order to overcome these shortcomings of the traditional algorithm,we proposed a foggy and hazy image enhancement algorithm based on Retinex in the fuzzy field.Firstly,the original image was classified into several blocks using the proposed adaptive multi-threshold algorithm,and then the optimal crossover points of the image blocking areas were computed.Secondly,we used a novel linear membership function to map the image pixel value into fuzzy domain,then computed the correlation parameter of the fuzzy hyperbolic tangent function by crossover points,used the Retinex algorithm to perform no-linear image enhancement,and used the fuzzy hyperbolic tangent functions to adjust the enhancement result.Finally,the method of superposition of the linear was used to map the enhancement result into original image domain.The experimental result shows that the “halo” effect is suppressed,the proposed method plays a better role in the image sharpness,image details and image fidelity,and it has more widely applicability.

Key words: Fuzzy field,Foggy and hazy image enhancement,Retinex algorithm,Fuzzy hyperbolic tangent function