High-order image subsampling using feedforward artificial neural networks

We propose a method for high-order image subsampling using feedforward artificial neural networks (FANNs). In our method, the high-order subsampling process is decomposed into a sequence of first-order subsampling stages. The first stage employs a tridiagonally symmetrical FANN, which is obtained by...

Description complète

Détails bibliographiques
Publié dans:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 10(2001), 3 vom: 15., Seite 427-35
Auteur principal: Dumitras, A (Auteur)
Autres auteurs: Kossentini, F
Format: Article en ligne
Langue:English
Publié: 2001
Accès à la collection:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Sujets:Journal Article
LEADER 01000caa a22002652 4500
001 NLM177376392
003 DE-627
005 20250209043819.0
007 cr uuu---uuuuu
008 231223s2001 xx |||||o 00| ||eng c
024 7 |a 10.1109/83.908518  |2 doi 
028 5 2 |a pubmed25n0591.xml 
035 |a (DE-627)NLM177376392 
035 |a (NLM)18249632 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Dumitras, A  |e verfasserin  |4 aut 
245 1 0 |a High-order image subsampling using feedforward artificial neural networks 
264 1 |c 2001 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Completed 20.05.2010 
500 |a Date Revised 05.02.2008 
500 |a published: Print 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a We propose a method for high-order image subsampling using feedforward artificial neural networks (FANNs). In our method, the high-order subsampling process is decomposed into a sequence of first-order subsampling stages. The first stage employs a tridiagonally symmetrical FANN, which is obtained by applying the design algorithm introduced by Dumitras and Kossentini (see IEEE Trans. Signal Processing, vol.48, p.1446-55, 2000). The second stage employs a small fully connected FANN. The algorithm used to train both FANNs employs information about local edges (extracted using pattern matching) to perform effective subsampling of both high detail and smooth image areas. We show that our multistage first-order subsampling method achieves excellent speed-performance tradeoffs, and it consistently outperforms traditional lowpass filtering and subsampling methods both subjectively and objectively 
650 4 |a Journal Article 
700 1 |a Kossentini, F  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on image processing : a publication of the IEEE Signal Processing Society  |d 1992  |g 10(2001), 3 vom: 15., Seite 427-35  |w (DE-627)NLM09821456X  |x 1057-7149  |7 nnns 
773 1 8 |g volume:10  |g year:2001  |g number:3  |g day:15  |g pages:427-35 
856 4 0 |u http://dx.doi.org/10.1109/83.908518  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 10  |j 2001  |e 3  |b 15  |h 427-35