Magnitude Sensitive Image Compression
Enrique Pelayo, David Buldain, Carlos Orrite
2013
Abstract
This paper introduces the Magnitude Sensitive Competitive Learning (MSCL) algorithm as a reliable and effi- cient approach for selective image compression. MSCL is a neural network that has the property of distributing the unit centroids in certain data-distribution zones according to a target magnitude locally calculated for every unit. This feature can be used for image compression to define the block images that will be compressed by Vector Quantization in a later step. As a result, areas of interest receive a lower compression than other parts in the image. Following this approach higher quality in the salient areas of a compressed image is achieved in relation to other methods.
References
- Ahmed, N., Natarajan, T., and Rao, K. R. (1974). Discrete cosine transform. Computers, IEEE Transactions on, 100(1):90-93.
- Amerijckx, C., Legat, J.-D., and Verleysen, M. (2003). Image compression using self-organizing maps. Systems Analysis Modelling Simulation, 43(11):1529-1543.
- Cheung, Y. (2005). On rival penalization controlled competitive learning for clustering with automatic cluster number selection. IEEE Transactions on Knowledge Data Engineering, (17):1583-1588.
- Computer Vision Group, U. o. G. (2002). Dataset of standard 512x512 grayscale test images. http://decsai.ugr.es/cvg/CG/base.htm.
- Harandi, M. and Gharavi-Alkhansari, M. (2003). Low bitrate image compression using self-organized kohonen maps. In Proceedings 2003 International Conference on Image Processing, ICIP'03, volume 3, pages 267-270.
- Harel, J., Koch, C., and Perona, P. (2006). Graph-based visual saliency. In NIPS'06, pages 545-552.
- Kohonen, T. (1998). The self-organizing map. Neurocomputing, 21(1):1-6.
- Laha, A., Pal, N., and Chanda, B. (2004). Design of vector quantizer for image compression using selforganizing feature map and surface fitting. Image Processing, IEEE Transactions on, 13(10):1291-1303.
- Liou, R.J., W. J. (2007). Image compression using sub-band dct featuresfor self-organizing map system. Journal of Computer Science and Application, 3(2).
- Pelayo, E., Buldain, D., and Orrite, C. (2013). Magnitude sensitive competitive learning. Neurocomputing, 112:4-18.
Paper Citation
in Harvard Style
Pelayo E., Buldain D. and Orrite C. (2013). Magnitude Sensitive Image Compression . In Proceedings of the 5th International Joint Conference on Computational Intelligence - Volume 1: NCTA, (IJCCI 2013) ISBN 978-989-8565-77-8, pages 370-380. DOI: 10.5220/0004552103700380
in Bibtex Style
@conference{ncta13,
author={Enrique Pelayo and David Buldain and Carlos Orrite},
title={Magnitude Sensitive Image Compression},
booktitle={Proceedings of the 5th International Joint Conference on Computational Intelligence - Volume 1: NCTA, (IJCCI 2013)},
year={2013},
pages={370-380},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004552103700380},
isbn={978-989-8565-77-8},
}
in EndNote Style
TY - CONF
JO - Proceedings of the 5th International Joint Conference on Computational Intelligence - Volume 1: NCTA, (IJCCI 2013)
TI - Magnitude Sensitive Image Compression
SN - 978-989-8565-77-8
AU - Pelayo E.
AU - Buldain D.
AU - Orrite C.
PY - 2013
SP - 370
EP - 380
DO - 10.5220/0004552103700380