An image topic model for image denoising

Topic model is a powerful tool for the basic document or image processing tasks. In this study we introduce a novel image topic model, called Latent Patch Model (LPM), which is a generative Bayesian model and assumes that the image and pixels are connected by a latent patch layer. Based on the LPM, we further propose an image denoising algorithm namely multiple estimate LPM (MELPM). Unlike other works, the proposed denoising framework is totally implemented on the latent patch layer, and it is effective for both Gaussian white noises and impulse noises. Experimental results demonstrate that LPM performs well in representing images. And its application in image denoising achieves competitive PSNR and visual quality with conventional algorithms.