Adaptive image quantisation techniques

This paper proposes three adaptive image quantisation techniques. These techniques calculate the quantisation levels using a method that is dependent on the images distribution pattern (hence the word 'adaptive') and then round off the pixels values to the nearest quantisation level. In this way, the number of different transmitted values is reduced. These schemes provide a wide range of compression ratios (CRs) with a very slight degradation of the signal to noise ratio (SNR). They are applied to both grey and colour images. The performances of these techniques are analysed and compared to other quantisation techniques to prove their quality. From the experimental results it is clear that they work well for all types of images and provide higher PSNR and perceptual quality than other techniques.