Authors: Monpraon Sukroongreung; Pratit Santiprabhob
Addresses: Faculty of Science and Technology, Assumption University, Ramkamhaeng 24 Road, Huamak, Bangkok 10240, Thailand ' Faculty of Science and Technology, Assumption University, Ramkamhaeng 24 Road, Huamak, Bangkok 10240, Thailand
Abstract: This paper outlines a framework that has been developed to assist in integrating components of a given face recognition system. By applying this framework, performance and restrictions of each component can be explicitly observed. Recognition performance of the resulting face recognition system can be clearly compared with components are replaced by other alternatives. The contribution of our work is a generalised framework for components integration of a face recognition system that facilitates: 1) examination of the effects of varying techniques and components to the recognition performance; 2) determination of suitable techniques, components and system configurations as per a given problem context. We have applied our framework to assemble different alternatives of a face recognitions system. Such applications reveal the effects when different components are included into a face recognition system and have shown insights into the relationship between dataset quality, techniques selected and recognition performance. This paper also outlines how the proposed framework can be applied to other biometric recognition systems.
Keywords: integration frameworks; component selection; biometrics; system integration; biometric standards; technique selection; face recognition.
International Journal of Biometrics, 2014 Vol.6 No.4, pp.335 - 362
Available online: 27 Jan 2015 *Full-text access for editors Access for subscribers Purchase this article Comment on this article