Title: Towards a robust palmprint representation for person identification
Authors: Abdallah Meraoumia; Hakim Bendjenna; Salim Chitroub
Addresses: Fac. des nouvelles technologies de l'information et de la communication, University of Ouargla, Lab. de Génie Électrique, Ouargla 30 000, Algeria ' Laboratory of Mathematics, Informatics and Systems (LAMIS), University of Larbi Tebessi, Tebessa, 12002, Algeria ' Laboratory of Intelligent and Communication Systems Engineering (LISIC), University of Houari Boumediene, Algiers, Algeria
Abstract: Biometrics, which refers to automatic identification of individuals based on their physiological and/or behavioural characteristics, is a widely studied field. Among the physiological biometric modalities, those based on palm have received the most attention due to its steady and unique features, which are rich in information with a low resolution. Although there is several palm capture devices, however, no of them is apt to provide the full features of the same palm. By using different capture devices, the palm features can be represented with different formats such as: greyscale images, near-infrared images, colour images, multispectral images and 3D shapes. In this context, we present in this paper a study that permits to propose robust palmprint representation for a reliable person identification system. Thus, a comparative study of the used palmprint image representations in the practice is performed using several databases each one contains 400 users.
Keywords: biometrics; person identification; palmprint; feature extraction; contourlet transform; hidden Markov model; HMM; data fusion.
International Journal of Information and Communication Technology, 2019 Vol.14 No.1, pp.89 - 109
Accepted: 01 Jun 2016
Published online: 07 Dec 2018 *