Title :
Efficient high-order image subsampling using FANNs
Author :
A. Dumitras;F. Kossentini
Author_Institution :
Dept. of Electr. & Comput. Eng., British Columbia Univ., Vancouver, BC, Canada
Abstract :
We propose a method for high-order image subsampling using feedforward artificial neural networks (FANNs). Our method employs a tridiagonally symmetrical FANN, which is obtained by applying the design algorithm proposed by Dumitraa and Kossentini (see IEEE Transactions on Signal Processing, vol.48, no.5, p.1446-55, 2000), and a small, fully connected FANN. We show that our subsampling method provides excellent speed-performance tradeoffs as compared to those of the method based exclusively on fully connected FANNs.
Keywords :
"Artificial neural networks","High definition video","Filtering","Algorithm design and analysis","Image decomposition","Image sampling","Signal sampling","Image converters","Digital TV","Motion estimation"
Conference_Titel :
Image Processing, 2000. Proceedings. 2000 International Conference on
Print_ISBN :
0-7803-6297-7
DOI :
10.1109/ICIP.2000.899373
