Adaptive kernel regression and probabilistic self-organizing maps for JPEG image deblocking

Perhaps the most widely used format for lossy compression of still images is JPEG (Joint Photographic Experts Group). In this image format the quality loss and an important part of the file size reduction come from the application of the Discrete Cosine Transform (DCT), and the subsequent quantization of its coefficients. These processes lead to noticeable compression artifacts. In this paper we present an intelligent system which is capable of analyzing a compressed JPEG image by combining the knowledge extracted from the image domain and the transformed domain, so that the results are restored versions that are more similar to both the original from the qualitative and quantitative points of view. It builds an approximation of the original image by kernel regression, which is controlled by self-organizing neural maps, so that the resulting image does not suffer from oversmoothing.