Reconstruction of Fingerprint Shape using Fractal Interpolation

One of the severe problems in a fingerprint-based system is retaining the fingerprint images. In this paper, we propose a method to minimize the fingerprint images size and retain the reference points. The method is divided into three parts, the first part is about digital image preprocessing that allows us to eliminate the noise, improve the image, convert it into a binary image, detect the skeleton and locate the reference point. The second part concerns the detection of critical points by the Douglas-Peucker method. The final part presents the methodology for the fingerprint curves reconstruction using the fractal interpolation curves. The experimental result shows the accuracy of this reconstruction method. The relative error (ER) is between 2.007% and 5.627% and the mean squared error (MSE) is between 0.126 and 0.009 at a small iterations number. On the other hand, for a greater number of iterations, the ER is between 0.415% and 1.64% and MSE is between 0.000124 and 0.0167. This clearly indicates that the interpolated curves and the original curves are virtually identical and exceedingly close.

@article{Bajahzar2019,
  title     = {Reconstruction of Fingerprint Shape using Fractal Interpolation},
  journal   = {International Journal of Advanced Computer Science and Applications},
  volume    = {10},
  number    = {5},
  year      = {2019},
  publisher = {The Science and Information Organization},
  author    = {Abdullah Bajahzar and Hichem Guedri},
  doi       = {10.14569/IJACSA.2019.0100514},
  url       = {https://doi.org/10.14569/IJACSA.2019.0100514}
}