A comparative study between ISITRA and wavelet filters

Author

Singh, Yumnam Kirani ; Parui, Swapzui Kumar ; Banerjee, Shuvransu

Author_Institution

Comput. Vision & Pattern Recognition Unit, Indian Stat. Inst., Kolkata, India

fYear

2004

fDate

20-22 Dec. 2004

Firstpage

333

Lastpage

337

Abstract

ISITRA is a new scheme of signal decomposition and reconstruction. In ISITRA, the space of PRF sets is much larger and more well-behaved than that in the existing schemes like filter bank or wavelets. Since such a space is constrained, it is mapped to an unconstrained space in which an optimization technique can be applied to find optimal PRF sets in terms of some criterion. Our criterion here is based on mean square error and the optimization technique used is genetic algorithms. Optimal PRF sets thus found perform better than the popular Daubechies´ filters for a compression task.

Keywords

data compression; genetic algorithms; image coding; image reconstruction; mean square error methods; wavelet transforms; ISITRA; genetic algorithm; image compression; mean square error; optimal PRF set; optimization technique; signal decomposition; signal reconstruction; unconstrained space mapping; wavelet filter; Discrete transforms; Discrete wavelet transforms; Filter bank; Genetic algorithms; Image coding; Image reconstruction; Mean square error methods; Mirrors; PSNR; Signal resolution;

fLanguage

English

Publisher

ieee

Conference_Titel

India Annual Conference, 2004. Proceedings of the IEEE INDICON 2004. First

Print_ISBN

0-7803-8909-3

Type

conf

DOI

10.1109/INDICO.2004.1497766

Filename

1497766