ON THE CONTRIBUTION OF COMPRESSION TO VISUAL PATTERN RECOGNITION

Gunther Heidemann, Helge Ritter

2008

Abstract

Most pattern recognition problems are solved by highly task specific algorithms. However, all recognition and classification architectures are related in at least one aspect: They rely on compressed representations of the input. It is therefore an interesting question how much compression itself contributes to the pattern recognition process. The question has been answered by Benedetto et al. (2002) for the domain of text, where a common compression program (gzip ) is capable of language recognition and authorship attribution. The underlying principle is estimating the mutual information from the obtained compression factor. Here we show that compression achieves astonishingly high recognition rates even for far more complex tasks: Visual object recognition, texture classification, and image retrieval. Though, naturally, specialized recognition algorithms still outperform compressors, our results are remarkable, since none of the applied compression programs (gzip , bzip2 ) was ever designed to solve this type of tasks. Compression is the only known method that solves such a wide variety of tasks without any modification, data preprocessing, feature extraction, even without parametrization. We conclude that compression can be seen as the “core” of a yet to develop theory of unified pattern recognition.

Paper Citation

in Harvard Style

Heidemann G. and Ritter H. (2008). ON THE CONTRIBUTION OF COMPRESSION TO VISUAL PATTERN RECOGNITION . In Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008) ISBN 978-989-8111-21-0, pages 83-89. DOI: 10.5220/0001078000830089

in Bibtex Style

@conference{visapp08,
author={Gunther Heidemann and Helge Ritter},
title={ON THE CONTRIBUTION OF COMPRESSION TO VISUAL PATTERN RECOGNITION},
booktitle={Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008)},
year={2008},
pages={83-89},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001078000830089},
isbn={978-989-8111-21-0},
}

in EndNote Style

TY - CONF
JO - Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008)
TI - ON THE CONTRIBUTION OF COMPRESSION TO VISUAL PATTERN RECOGNITION
SN - 978-989-8111-21-0
AU - Heidemann G.
AU - Ritter H.
PY - 2008
SP - 83
EP - 89
DO - 10.5220/0001078000830089