Recreating Fingerprint Images by Convolutional Neural Network Autoencoder Architecture

Fingerprint recognition systems have been applied widely to adopt accurate and reliable biometric identification between individuals. Deep learning, especially Convolutional Neural Network (CNN) has made a tremendous success in the field of computer vision for pattern recognition. Several approaches...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Sergio Saponara, Abdussalam Elhanashi, Qinghe Zheng
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Fingerprint images convolution neural networks autoencoder feature extraction system identification Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/dcba48f5a187474189ffe3a7e3b2a461
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:dcba48f5a187474189ffe3a7e3b2a461
record_format	dspace
spelling	oai:doaj.org-article:dcba48f5a187474189ffe3a7e3b2a4612021-11-18T00:07:31ZRecreating Fingerprint Images by Convolutional Neural Network Autoencoder Architecture2169-353610.1109/ACCESS.2021.3124746https://doaj.org/article/dcba48f5a187474189ffe3a7e3b2a4612021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9598889/https://doaj.org/toc/2169-3536Fingerprint recognition systems have been applied widely to adopt accurate and reliable biometric identification between individuals. Deep learning, especially Convolutional Neural Network (CNN) has made a tremendous success in the field of computer vision for pattern recognition. Several approaches have been applied to reconstruct fingerprint images. However, these algorithms encountered problems with various overlapping patterns and poor quality on the images. In this work, a convolutional neural network autoencoder has been used to reconstruct fingerprint images. An autoencoder is a technique, which is able to replicate data in the images. The advantage of convolutional neural networks makes it suitable for feature extraction. Four datasets of fingerprint images have been used to prove the robustness of the proposed architecture. The dataset of fingerprint images has been collected from various real resources. These datasets include a fingerprint verification competition (FVC2004) database, which has been distorted. The proposed approach has been assessed by calculating the cumulative match characteristics (CMC) between the reconstructed and the original features. We obtained promising results of identification rate from four datasets of fingerprints images (Dataset I, Dataset II, Dataset III, Dataset IV) with 98.1%, 97%, 95.9%, and 95.02% respectively by CNN autoencoder. The proposed architecture was tested and compared to the other state-of-the-art methods. The achieved experimental results show that the proposed solution is suitable for recreating a complex context of fingerprinting images.Sergio SaponaraAbdussalam ElhanashiQinghe ZhengIEEEarticleFingerprint imagesconvolution neural networksautoencoderfeature extractionsystem identificationElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 147888-147899 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Fingerprint images convolution neural networks autoencoder feature extraction system identification Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Fingerprint images convolution neural networks autoencoder feature extraction system identification Electrical engineering. Electronics. Nuclear engineering TK1-9971 Sergio Saponara Abdussalam Elhanashi Qinghe Zheng Recreating Fingerprint Images by Convolutional Neural Network Autoencoder Architecture
description	Fingerprint recognition systems have been applied widely to adopt accurate and reliable biometric identification between individuals. Deep learning, especially Convolutional Neural Network (CNN) has made a tremendous success in the field of computer vision for pattern recognition. Several approaches have been applied to reconstruct fingerprint images. However, these algorithms encountered problems with various overlapping patterns and poor quality on the images. In this work, a convolutional neural network autoencoder has been used to reconstruct fingerprint images. An autoencoder is a technique, which is able to replicate data in the images. The advantage of convolutional neural networks makes it suitable for feature extraction. Four datasets of fingerprint images have been used to prove the robustness of the proposed architecture. The dataset of fingerprint images has been collected from various real resources. These datasets include a fingerprint verification competition (FVC2004) database, which has been distorted. The proposed approach has been assessed by calculating the cumulative match characteristics (CMC) between the reconstructed and the original features. We obtained promising results of identification rate from four datasets of fingerprints images (Dataset I, Dataset II, Dataset III, Dataset IV) with 98.1%, 97%, 95.9%, and 95.02% respectively by CNN autoencoder. The proposed architecture was tested and compared to the other state-of-the-art methods. The achieved experimental results show that the proposed solution is suitable for recreating a complex context of fingerprinting images.
format	article
author	Sergio Saponara Abdussalam Elhanashi Qinghe Zheng
author_facet	Sergio Saponara Abdussalam Elhanashi Qinghe Zheng
author_sort	Sergio Saponara
title	Recreating Fingerprint Images by Convolutional Neural Network Autoencoder Architecture
title_short	Recreating Fingerprint Images by Convolutional Neural Network Autoencoder Architecture
title_full	Recreating Fingerprint Images by Convolutional Neural Network Autoencoder Architecture
title_fullStr	Recreating Fingerprint Images by Convolutional Neural Network Autoencoder Architecture
title_full_unstemmed	Recreating Fingerprint Images by Convolutional Neural Network Autoencoder Architecture
title_sort	recreating fingerprint images by convolutional neural network autoencoder architecture
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/dcba48f5a187474189ffe3a7e3b2a461
work_keys_str_mv	AT sergiosaponara recreatingfingerprintimagesbyconvolutionalneuralnetworkautoencoderarchitecture AT abdussalamelhanashi recreatingfingerprintimagesbyconvolutionalneuralnetworkautoencoderarchitecture AT qinghezheng recreatingfingerprintimagesbyconvolutionalneuralnetworkautoencoderarchitecture
_version_	1718425254617939968

Recreating Fingerprint Images by Convolutional Neural Network Autoencoder Architecture

Ejemplares similares