engleski

A NEW ADAPTIVE BLENDING PREDICTOR FOR LOSSLESS IMAGE COMPRESSION

Medical image compression is a growing need in the era of large amount of image data stored in contemporary health care systems. In the article we propose a novel method for lossless medical image compression based on predictive models and entropy coding. The predictor models the image properties around the current, unknown pixel and adjusts itself to the local image region. The main contribution of this work is the enhancement of the well known approach of predictor blends through highly adaptive determination of blending context on a pixel-by-pixel basis using classification technique. This allows modeling of more complex image structures such as nontrivially oriented edges and the periodicity and coarseness of textures.

Lossless Image Compression; Predictive Coding; Predictor Blends

nije evidentirano