Lossless image coding via adaptive linear prediction and classification

In the past years, there have been several improvements in lossless image c ompression. All the recently proposed state-of-the-art lossless image compr essors can be roughly divided into two categories: single and double-pass c ompressors. Linear prediction is rarely used in the first category, while T MV [7], a state-of-the-art double-pass image compressor, relies on linear p rediction for its performance. We propose a single-pass adaptive algorithm that uses context classificatio n and multiple linear predictors, locally optimized on a pixel-by-pixel bas is. Locality is also exploited in the entropy coding of the prediction erro r. The results we obtained on a test set of several standard images are enc ouraging. On the average, our ALPC obtains a compression ration comparable to CALIC [20] while improving on some images.