Toward a compression-based self-organizing recognizer: Preliminary implementation of PRDC-CSOR

• Compressibility of a data x   is an approximation of the Kolmogorov complexity K(x)K(x).
• Compressibility can be a new general data’s feature for pattern recognition.
• This possibility is shown through the preliminary implementation of the PRDC-CSOR.
• PRDC-CSOR can build the pattern recognition function using incoming data only.
• Preliminary application to image data gave promising results.

The present paper introduces a new data analyzer, a compression-based self-organizing recognizer, the PRDC-CSOR (Pattern Representation scheme using Data Compression – Compression based Self ORganizing Recognizer), with a preliminary application to image data. The PRDC-CSOR is an extension of the authors’ previously proposed pattern representation scheme using data compression (PRDC). Contrary to the traditional statistical-model-based recognition system methods, the PRDC-CSOR constructs itself using incoming data only. The basic tool, compressibility, is an approximation of the Kolmogorov complexity K(x)K(x) defined in an individual text x   as a countermeasure against the Shannon entropy H(X)H(X) defined on an ensemble X. Due to this feature, a highly automatic self-organizing recognition system becomes possible as demonstrated in this paper.