An Adaptive Short Time Beltrami Kernel for Image De-Noising

Short time Beltrami kernel is a well known method for image de-noising using diffusion on image manifold. In this paper we propose an adaptive short time Beltrami. In the proposed method we adapt an effective parameter in Beltrami algorithm according to local variance of image. To evaluate the performance of the proposed method, several comparative experiments are performed. The obtained results confirm the efficiency of the proposed method.