Title :
PPM Revisited with New Idea on Escape Probability Estimation
Author :
Sayyed, Azaruddin ; Agarwal, Suneeta
Author_Institution :
MNNIT, Allahabad
Abstract :
A variant of prediction by partial matching scheme with a modification of escape probability estimation is presented here. This paper gives a new method for bounded length context models with static estimation of escape probability. The experimental results have shown that the proposed technique performs better with a compression rate of 2.35 b/Character among all the bounded length PPM compression schemes. It is also observed that this method shows better results on files having binary data rather than character data.
Keywords :
data compression; image coding; probability; PPM; bounded length context models; character data; compression rate; compression schemes; escape probability estimation; partial matching scheme; static estimation; Application software; Arithmetic; Compression algorithms; Computational intelligence; Computer science; Context modeling; Data compression; Encoding; Predictive models; Probability;
Conference_Titel :
Conference on Computational Intelligence and Multimedia Applications, 2007. International Conference on
Conference_Location :
Sivakasi, Tamil Nadu
Print_ISBN :
0-7695-3050-8
DOI :
10.1109/ICCIMA.2007.262