Congrats and thanks to Dr. Naserasadi for his collaboration on our recently accepted paper with the title of "Chaos game theory and its application for offline signature identification" in prestigious peer-reviewed journal IET Biometrics.

 

Chaos game theory and its application for offline signature identification

Mahdi Jampour and Ali Naserasadi

Abstract

Chaos game mechanism is a procedure for creating fractal phenomena from another fractal using a polygon and random walk. Here, the authors propose a novel identification approach and efficient application of Chaos Game theory towards signature identification. In fact, a signature is produced with hand scripting with a special rhythm that belongs to a specific person. Although a signature is a behavioural feature among the human biometric features, this behavioural feature expresses a chaotic property and can be analysed with chaotic systems and fractal theory. With authors’ technique, by using a Chaos Game theory, a new fractal is created for each signature instance and, during the creation of the fractal, new features are extracted. These features express the fractal properties of the signature and are unique. In addition, by using fractal theory, this technique benefits from the advantages of fractal phenomena such as stability against rotation, losing some parts of the signature and scale that is desirablefor biometrics applications. Authors’ approach for offline signature analysis can segregate and identify many signature instances with a desirable time complexity. The authors name the technique that the authors present here the chaos game signature identification (CGSI).

 

https://digital-library.theiet.org/content/journals/10.1049/iet-bmt.2018.5188

 

This project is open and we update it regularlgy. 17/11/2018.

Preparing_Gen_Fractals.m is a function that receive a signature image and generate fractal-like image in square shape.
the output is an image contains 18 time rotated of input signature. 27/11/2018.

ChaosGame.m is a Matlab code with two input arguments (image, scale)
image is in Uint8 format and scale is the distance between random point and four considered points (please read the paper). the default value of scale is 3.
The output is a histogram in form Hist(1, 5) that present the signature features. 29/11/2018.
 

 Please cite our paper if you find it useful