A Novel Approach for Automatic Enhancement of Fingerprint Images via Deep Transfer Learning

2020 International Joint Conference on Neural Networks (IJCNN)

Aldísio Gonçalves Medeiros4,5   João Pedro Bernardino Andrade1,4   Paulo Bruno de Sousa Serafim4
Alexandre Magno Monte Santos1,4   José Gilvan Rodrigues Maia2,4   Fernando Antonio Mota Trinta1,4
José Antônio Fernandes de Macêdo3,4   Pedro Pedrosa Rebouças Filho4,5   Paulo Antonio Leal Rego1,4

1Group of Computer Networks, Software Engineering and Systems (GREat)
2Virtual UFC Institute  3Insight Data Science Lab  4Federal University of Ceará (UFC)
5Laboratório de Processamento de Imagens, Sinais e Computação Aplicada (LAPISCO), Federal Institute of Ceará

General procedure


Page: [IEEE]

Abstract

For any Automated Fingerprint Identification System, the quality of its images is vital to ensure the proper accuracy of the whole system. When the quality of an image is not satisfactory, enhancement processes may be applied to help the extraction of the fingerprint features. There are several enhancement techniques, and their suitability depends on the features of the original fingerprint image. Choosing the best enhancement method is crucial because these procedures do not always improve the image quality, and may even worsen it. This work addresses this topic and presents a classifier based on Convolutional Neural Networks (CNNs) that automatically chooses the most suitable enhancement method for a specific image and applies it, but only if necessary. Our solution avoids an excessive human effort to select the best enhancement process and also requires no further training. We evaluated our proposal using FVCs datasets, and results show the benefits of CNN-based feature extractors and that our solution was able to improve the quality of digital printing through the adaptive application of enhancement filters.

BitTeX

Download

@InProceedings{medeiros2020novel,
  title = {A Novel Approach for Automatic Enhancement of Fingerprint Images via Deep Transfer Learning},
  author  = {Medeiros, Ald\'{i}sio Gon\c{c}alves and
    Andrade, Jo{\~{a}}o Pedro Bernardino and
    Serafim, Paulo Bruno Sousa and
    Santos, Alexandre Magno Monte and
    Maia, Jos\'{e} Gilvan Rodrigues and
    Trinta, Fernando Antonio Mota and
    Mac\^{e}do, Jos\'{e} Antônio Fernandes and
    {Rebou\c{c}as Filho}, Pedro Pedrosa and
    Rego, Paulo Antonio Leal},
  booktitle = {2020 International Joint Conference on Neural Networks (IJCNN)},
  pages = {1--8},
  year = {2020},
  doi = {10.1109/IJCNN48605.2020.9206836}
}