Genuine art object judgment method and system using markov chain

摘要

The present invention relates to a system and method for discriminating forgery of an artwork using a Markov chain, in which an image of an artwork as an appraisal object is subjected to respective processes consisting of a color type analysis method and an entropy type analysis method, and is synthesized such that the authenticity of the artwork is showed with probability, thereby providing high accuracy. The system according to the present invention comprises: a database unit for storing an image file of an original artwork and storing color difference signal information and statistical sign information on entropy of the entire original image; an image extracting unit for acquiring image information of the artwork corresponding to the discrimination target; a color type analyzing unit for dividing each image of the image extracting unit according to a color difference signal and applying a Markov chain to each pixel so as to perform comparison with the color difference information stored in the database unit; an entropy type analyzing unit for quantizing and statistically encoding the entropy of each image of the image extracting unit, and comparing the encoding result with the statistical sign information stored in the database unit in the Markov chain manner; and a discrimination calculating unit for calculating the similarity to the original artwork by analyzing a relationship for the result values of the color type analysis unit and the entropy type analysis unit.