An ensemble learning approach to lip-based biometric verification, with a dynamic selection of classifiers. (January 2019)

• Record Type: Journal Article
• Authors: Porwik, Piotr; Doroz, Rafal; Wrobel, Krzysztof
• Is Part Of: Expert systems with applications. Volume 115(2019)
• Page Start: 673
• Page End: 683
• Publication Date: 2019-01
• Subjects: Lip-based biometrics -- Dynamic classifiers selection -- Pattern recognition -- Ensemble classification -- Person verification; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2018.08.037
• Languages: English
• ISSNs: 0957-4174

Abstract

Highlights: Ensemble classifier system is applied to biometric verification. For each base classifier, the classifier's competence is separately calculated. A lip geometrical features measurements are proposed. Experiments confirmed our method outperforms other state-of-the-art methods. Abstract: Machine learning approaches are largely focused on pattern or object classification, where a combination of several classifier systems can be integrated to help generate an optimal or suboptimal classification decision. Multiple classification systems have been extensively developed because a committee of classifiers, also known as an ensemble, can outperform the ensemble's individual members. In this paper, a classification method based on an ensemble of binary classifiers is proposed. Our strategy consists of two phases: (1) the competence of the base heterogeneous classifiers in a pool is determined, and (2) an ensemble is formed by combining those base classifiers with the greatest competences for the given input data. We have shown that the competence of the base classifiers can be successfully calculated even if the number of their learning examples was limited. Such a situation is particularly observed with biometric data. In this paper, we propose a new biometric data structure, the Sim coefficients, along with an efficient data processing technique involving a pool of competent classifiers chosen by dynamic selection.