A CI-MSPCNN image enhancement method based on Dunhuang murals

In the process of Dunhuang mural painting image restoration, image enhancement technology effectively improves the image quality and restoration effect. In this paper, a cognitive-integrated modified simplified pulse-coupled neural network (CI-MSPCNN) model is proposed based on the fire-controlled modified simplified pulse-coupled neural network (FC-MSPCNN) model, aiming to solve the problem of low-light illumination in Dunhuang mural painting images. Neural network (CI-MSPCNN) model, which aims to solve the low-light problem of Dunhuang mural images. The model improves the model's performance and adaptability by optimizing the synaptic weight matrix, simplifying the computation process and merging the link strength and weight matrices, as well as introducing a dynamic threshold adjustment mechanism, which better simulates human visual features. Finally, the linear transform, gamma transform, and histogram algorithms are used for image enhancement and compared with the CI-MSPCNN model. The experimental results show that the CI-MSPCNN model proposed in this paper shows good results in enhancing low-light images.