Title :

An Improved Multispectral Palmprint System Using Deep CNN-based Palm-Features

Author(s) :

Trabelsi, Selma [Auteur]
Samai, Djamel [Auteur]
Meraoumia, Abdallah [Auteur]
Bensid, Khaled [Auteur]
Tahleb Ahmed, Abdelmalik [Auteur]
COMmunications NUMériques - IEMN [COMNUM - IEMN]
Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 [IEMN]

Conference title :

International Conference on Advanced Electrical Engineering (ICAEE 2019)

City :

Algiers

Country :

Algérie

Start date of the conference :

2019-11-19

Publisher :

IEEE

English keyword(s) :

Feature extraction
Security
Physiology
Databases
Convolutional neural networks
Machine learning
Biometrics (access control)

HAL domain(s) :

Informatique [cs]
Informatique [cs]/Intelligence artificielle [cs.AI]
Informatique [cs]/Réseaux et télécommunications [cs.NI]
Sciences de l'ingénieur [physics]
Sciences de l'ingénieur [physics]/Traitement du signal et de l'image [eess.SP]
Sciences de l'ingénieur [physics]/Electronique

English abstract : [en]

Due to security imperatives, biometrics has attracted a lot of attention in recent decades. Biometric recognition refers to the identification of individuals based on their physiological and/or behavioral traits. Among the ...
Show more >Due to security imperatives, biometrics has attracted a lot of attention in recent decades. Biometric recognition refers to the identification of individuals based on their physiological and/or behavioral traits. Among the various physiological traits, the palmprint modality, which contains rich biometric features, has become one of the essential features that prove their effectiveness in improving the biometric recognition system accuracy. In addition to the palmprint texture features, infrared light can capture the vein-net of the palm, an independent biometric trait called palm-vein. Fortunately, these two biometric modalities can be easily obtained with a multispectral device and thus used together to enhance the biometric system. In this paper, we attempt to extract deep biometric features using a Convolutional Neural Network (CNN) to develop an effective deep-learning based multispectral palmprint recognition system. The tests results of extensive experiments conducted on a large and public palmprint multispectral database show that the proposed scheme effectively improves recognition results, mainly when fusing spectral bands of biometric modality.Show less >

Language :

Anglais

Peer reviewed article :

Oui

Audience :

Internationale

Popular science :

Non

Collections :

• Institut d'Électronique, de Microélectronique et de Nanotechnologie (IEMN) - UMR 8520

Source :

Harvested from HAL