Mycielski Based 2d-Predictive Image Coding Algorithm

Abstract:

The Mycielski method is a prospering prediction algorithm which is based on searching and finding largest repeated binary patterns. It uses infinite-past data to devise a rule based prediction method on a time series. In this work, a novel two-dimensional (image processing) version of the Mycielski algorithm is proposed. Since the dimensionality definition of “past” data increases in two-dimensional signals, the proposed algorithm also needs to handle how the boundaries of the pixel cliques are iteratively extended in the neighborhood of a current pixel. The clique extension invokes novel similarity search strategies that depend on the chosen physical distance metric. The proposed prediction algorithm is used for predictive image compression and performance comparisons with other predictive coding methods are presented.

• Periodical: Applied Mechanics and Materials (Volume 850)
• Pages: 144-151
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.850.144
• Online since: August 2016
• Authors: Mehmet Fidan*, Omer Nezih Gerek
• Keywords: Image Compression, Mycielski, Prediction, Predictive Coding

References

[1] M. J. Weinberger, G. Seroussi, and G. Sapiro, LOCO-I: A low complexity, context-based, lossless image compression algorithm, Dcc '96 - Data Compression Conference Proceedings (1996) 140-149.

DOI: 10.1109/dcc.1996.488319

[2] M. J. Weinberger, G. Seroussi, and G. Sapiro, The LOCO-I Lossless Image Compression Algorithm: Principles and Standardization into JPEG-LS, Hewlett-Packard Laboratories 236, (1998).

DOI: 10.1109/83.855427

[3] X. L. Wu and N. Memon, Context-based, adaptive, lossless image coding, IEEE Transactions on Communications 45 (1997) 437-444.

DOI: 10.1109/26.585919

[4] P. Maragos, R. W. Schafer, and R. M. Mersereau, Two-dimensional linear prediction and its application to adaptive predictive coding of images, IEEE Transactions on Acoustics, Speech and Signal Processing 32 (1984) 1213-1229.

DOI: 10.1109/tassp.1984.1164463

[5] P. Jacquet, W. Szpankowski, and I. Apostol, A universal predictor based on pattern matching, IEEE Transactions on Information Theory 48 (2002) 1462-1472.

DOI: 10.1109/tit.2002.1003834

[6] F. O. Hocaoğlu, M. Fidan, and Ö. N. Gerek, Mycielski approach for wind speed prediction, Energy Conversion and Management 50 (2009) 1436-1443.

DOI: 10.1016/j.enconman.2009.03.003

[7] M. Fidan, F. O. Hocaoglu, and O. N. Gerek, Improved synthetic wind speed generation using modified Mycielski approach, International Journal of Energy Research 36 (2012) 1226-1237.

DOI: 10.1002/er.1893

[8] A. Ehrenfeucht and J. Mycielski, A Pseudorandom Sequence-How Random Is It?, American Mathematical Monthly (1992) 373-375.

DOI: 10.1080/00029890.1992.11995863

[9] M. Fidan and O. Gerek, Randomness analysis of Antimycielski number generator, IEEE 16th Signal Processing, Communication and Applications Conference, SIU 2008. (2008) 1-4.

DOI: 10.1109/siu.2008.4632596

[10] M. Fidan and Ö. Gerek, A time improvement over the Mycielski algorithm for predictive signal coding: Mycielski-78, Proc. 14th European Signal Processing Conference EUSIPCO (2006).

DOI: 10.1109/siu.2009.5136524

[11] W. D. Shannon, 11 Cluster Analysis, in: J. P. M. C.R. Rao and D. C. Rao (Eds. ), Handbook of Statistics, vol. 27, Elsevier, 2007, pp.342-366.

[12] G. Forney Jr, Generalized minimum distance decoding, IEEE Transactions on Information Theory 12 (1966) 125-131.

DOI: 10.1109/tit.1966.1053873

[13] F. Hocaoglu, M. Fidan, and O. Gerek, Mycielski approach for synthetic wind speed data generation, IEEE 17th Signal Processing and Communications Applications Conference, SIU 2009. (2009) 836-839.

DOI: 10.1109/siu.2009.5136526