The images are usually degraded during capturing and transferring. To improve the quality of images, a method that uses the local contrast information combined with the entropy concept to suppress the non-linear noise in images is described here. Furthermore, images are also enhanced by local contrast information. This method is compared with other classic denoising methods, such as median filter, Lee filter, Frost filter and so on. The experimental results of the simulations and application to synthetic noised images and infrared images prove the good performance of the proposed method.