Data preprocessing for adaptive vector quantization

摘要

This paper describes a method for designing a codebook for vector quantization (VQ), based on preprocessing of the input data which makes them block-stationary, and on a criterion which takes into account the error visibility of the image to be coded. Test results, carried out at about 1.2 bits/pel bit rate, indicate that the proposed VQ enables reconstruction of images (both outside and inside the training set) with very low distortion, and exhibits high robustness, the variance of the SNR being sensibly lower than in the case of unprocessed data.