A Method based on Convolutional Neural Networks for Fingerprint Segmentation

2019 International Joint Conference on Neural Networks (IJCNN)

Paulo Bruno de Sousa Serafim1,5   Aldísio Gonçalves Medeiros1,5   Paulo Antonio Leal Rego1,5
José Gilvan Rodrigues Maia2,5   Fernando Antonio Mota Trinta1,5   Marcio Espíndola Freire Maia6
José Antônio Fernandes de Macêdo3,5   Aloísio Vieira Lira Neto4

1Group of Computer Networks, Software Engineering and Systems (GREat)  2Virtual UFC Institute
3Insight Data Science Lab  4Brazilian Federal Highway Police
5Federal University of Ceará (UFC), Fortaleza, Ceará, Brazil  6Federal University of Ceará (UFC), Quixadá, Ceará, Brazil

General procedure

ROI results comparison


Page: [IEEE]

Abstract

In forensic science, the resolution of crimes is associated with the identification of those involved. In the civil context, the security of automated processes depends on the identification of authorized people. In this sense, fingerprint-based recognition techniques stand out. A fundamental stage is the calculation of the degree of similarity between the samples presented, so the task of identifying a region of interest (ROI), excluding noisy regions, can improve the precision and reduce the computational cost. In this aspect, this work presents a technique of segmentation of the region of interest based on convolutional neural networks (CNN) without pre-processing steps. The new approach was evaluated in two different architectures from state of the art, presenting similarity indexes Distance of Hausdorff (5.92), Dice coefficient (97.28\%) and Jaccard Similarity (96.77\%) superior to the classic methods. The error rate (3.22\%) was better than five segmentation techniques from state of the art and showed better results than another deep learning approach, presenting promising results to identify the region of interest with potential for application in systems based on biometric identification.

BitTeX

Download

@InProceedings{serafim2019ijcnn,
  title = {A Method based on Convolutional Neural Networks for Fingerprint Segmentation},
  author  = {Serafim, Paulo Bruno Sousa and
    Medeiros, Ald\'{i}sio Gon\c{c}alves and
    Rego, Paulo Antonio Leal and
    Maia, Jos\'{e} Gilvan Rodrigues and
    Trinta, Fernando Antonio Mota and
    Maia, Marcio Esp\'{i}ndola Freire and
    Mac\^{e}do, Jos\'{e} Antônio Fernandes and
    Neto, Alo\'{i}sio Vieira Lira},
  booktitle = {2019 International Joint Conference on Neural Networks (IJCNN)},
  pages = {1--8},
  year = {2019},
  doi = {10.1109/IJCNN.2019.8852236}
}