Authors: Paweł Krotewicz
Addresses: Department of Microelectronics and Computer Science, Lodz University of Technology, Lodz, Poland
Abstract: This paper concerns the novel region-based ear-assisted 3D face recognition based on iterative closest point (ICP) algorithm in face expression changing scenario. The proposed algorithm for 3D face biometric recognition was prepared and tested. As a first contribution, current state-of-the-art in the field of 3D face recognition is presented and the main approaches to the problem are briefly described. Furthermore, all the data processing steps: preprocessing, segmentation, feature extraction and feature comparison are described in detail. As a second contribution, the algorithm behaviour is scrutinised on the DMCSv1 database and the results in the form of DET curves are highlighted in this paper. Also, the comparison with results obtained by means of the algorithm neglecting ear regions is provided. It occurs that ear geometry information added to face as an auxiliary input to iterative closest point can greatly improve recognition results especially in the case of very strong facial expressions. Equal error rate does not exceed 6.25% on arbitrary data subset. In the last section, conclusions are formulated and plans for future work are presented.
Keywords: biometrics; expression-invariant face recognition; biometric identification; contactless identification; 3D ear geometry; 3D face geometry; iterative closest point; ICP; feature-based system; region-based method; expression variations.
International Journal of Biometrics, 2016 Vol.8 No.1, pp.65 - 81
Available online: 19 Jun 2016 *Full-text access for editors Access for subscribers Purchase this article Comment on this article