A Generalized Fuzzy Complement Function for Low-light Image Enhancement

Classical fuzzy complement functions compute the non-membership grades of elements based solely on their membership values. However, they often fall short in effectively representing uncertainty in complex scenarios. Yager and Sugeno introduced alternative classes of fuzzy complement functions, which have been widely applied in image enhancement tasks to address uncertainty and poor illumination. In this study, a generalized fuzzy complement function is employed to develop a low-light image enhancement model. A novel contrast boosting approach is proposed to adaptively enhance image brightness and detail. Furthermore, a parameter search algorithm is introduced to fine-tune two key parameters in the fuzzy complement function, optimizing the enhancement process. Experimental results and comparisons with state-of-the-art methods demonstrate the superior performance of the proposed model.