Image Compression with Competitive Networks and Pre-fixed Prototypes

 

Abstract

Image compression techniques have required much attention from the neural networks community for the last years. In this work we intend to develop a new algorithm to perform image compression based on adding some pre-fixed prototypes to those obtained by a competitive neural network. Prototypes are selected to get a better representation of the compressed image, improving the computational time needed to encode the image and decreasing the code-book storage necessities of the standard approach. This new method has been tested with some well-known images and results proved that our proposal outperforms classical methods in terms of maximizing peak-signal-to-noise-ratio values. © 2007 International Federation for Information Processing.

Citation

Please, cite this work as:

[CLO07] E. M. Casermeiro, D. López-Rodríguez, and J. M. Ortiz-de-Lazcano-Lobato. “Image Compression with Competitive Networks and Pre-fixed Prototypes”. In: Artificial Intelligence and Innovations 2007: from Theory to Applications, Proceedings of the 4th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI 2007), 19-21 September 2007, Peania, Athens, Greece. Ed. by C. Boukis, A. Pnevmatikakis and L. Polymenakos. Vol. 247. IFIP. cited By 0. Springer, 2007, pp. 339-346. DOI: 10.1007/978-0-387-74161-1_37. URL: https://doi.org/10.1007/978-0-387-74161-1_37.

BibTeX

@InProceedings{Casermeiro2007c,
     author = {Enrique Mérida Casermeiro and Domingo López-Rodríguez and Juan Miguel Ortiz-de-Lazcano-Lobato},
     booktitle = {Artificial Intelligence and Innovations 2007: from Theory to Applications, Proceedings of the 4th {IFIP} International Conference on Artificial Intelligence Applications and Innovations {(AIAI} 2007), 19-21 September 2007, Peania, Athens, Greece},
     title = {Image Compression with Competitive Networks and Pre-fixed Prototypes},
     year = {2007},
     editor = {Christos Boukis and Aristodemos Pnevmatikakis and Lazaros Polymenakos},
     note = {cited By 0},
     pages = {339–346},
     publisher = {Springer},
     series = {{IFIP}},
     volume = {247},
     abstract = {Image compression techniques have required much attention from the neural networks community for the last years. In this work we intend to develop a new algorithm to perform image compression based on adding some pre-fixed prototypes to those obtained by a competitive neural network. Prototypes are selected to get a better representation of the compressed image, improving the computational time needed to encode the image and decreasing the code-book storage necessities of the standard approach. This new method has been tested with some well-known images and results proved that our proposal outperforms classical methods in terms of maximizing peak-signal-to-noise-ratio values. © 2007 International Federation for Information Processing.},
     bibsource = {dblp computer science bibliography, https://dblp.org},
     biburl = {https://dblp.org/rec/conf/ifip12/CasermeiroLO07.bib},
     document_type = {Conference Paper},
     doi = {10.1007/978-0-387-74161-1_37},
     journal = {IFIP International Federation for Information Processing},
     keywords = {Image compression; Image quality, Classical methods; Competitive network; Competitive neural network; Compressed images; Computational time; Image compression techniques; Peak signal to noise ratio, Artificial intelligence},
     source = {Scopus},
     url = {https://doi.org/10.1007/978-0-387-74161-1_37},
}