Writer Identification based on the fractal construction of a reference base

Our aim is to achieve writer identification process thanks to a fractal analysis of handwriting style. For each writer, a set of characteristics is extracted. They are specific to the writer. Advantage is taken from the autosimilarity properties that are present in one’s handwriting. In order to do that, some invariant patterns characterizing the writing are extracted. During the training step these invariant patterns appear along a fractal compression process, then they are organized in a reference base that can be associated with the writer. This base allows to analyze an unknown writing the writer of which has to be identified. A Pattern Matching process is performed using all the reference bases successively. The results of this analyze are estimated through the signal to noise ratio. Thus, the signal to noise ratio according to a set of bases identifies the unknown text’s writer.