Authors: Maarouf Korichi; Abdallah Meraoumia; Kamal Eddine Aiadi
Addresses: Lab. de Génie Électrique (LAGE), Fac. des nouvelles technologies, de l'information et de la communication, Univ. Ouargla, Ouargla 30000, Algeria ' Laboratory of Mathematics, Informatics and Systems (LAMIS), University of Larbi Tebessi, Tebessa, 12002, Algeria ' Lab. développement des Énergie Nouvelle et Renouvelables dans les Zones Arides et Saharienne (LENREZA), Fac. des mathématique et science de matriére, Univ. Ouargla, Ouargla 30000, Algeria
Abstract: In any computer vision application, integration of relevant feature extraction module is vital to help in making accurate decision of the classification. In the literature, several methods that have achieved promising results and high accuracies are based on texture analysis. Thus, there exist various feature extraction techniques to describe the texture information, among them; the local binary pattern (LBP) is widely used to characterise the image sufficiently. Generally, LBP descriptor and their variants are applied on greyscale images. Thus, in this paper, we propose a new method that can be applied to any type of image either in greyscale, colour, multispectral or hyperspectral. It is a new scheme of 3D local binary pattern. We have developed biometric system for person identification and an edge detection technique to evaluate it. The obtained results have showed that it has higher performances compared to other methods developed in the literature in terms of identification rates.
Keywords: feature extraction; local binary pattern; LBP; biometrics; person identification; palmprint; data fusion.
International Journal of Information and Communication Technology, 2019 Vol.14 No.4, pp.439 - 455
Accepted: 04 Nov 2017
Published online: 23 Aug 2019 *