Title :
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
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;
Conference_Titel :
India Annual Conference, 2004. Proceedings of the IEEE INDICON 2004. First
Print_ISBN :
0-7803-8909-3
DOI :
10.1109/INDICO.2004.1497766
