2014 |
Križaj, Janez; Štruc, Vitomir; Mihelič, France A Feasibility Study on the Use of Binary Keypoint Descriptors for 3D Face Recognition Proceedings Article In: Proceedings of the Mexican Conference on Pattern Recognition (MCPR), pp. 142–151, Springer 2014. Abstract | Links | BibTeX | Tags: 3d face recognition, binary descriptors, biometrics, BRISK, CASIA, face verification, FREAK, FRGC, MCPR, ORB, performance evaluation, SIFT, SURF @inproceedings{krivzaj2014feasibility, Despite the progress made in the area of local image descriptors in recent years, virtually no literature is available on the use of more recent descriptors for the problem of 3D face recognition, such as BRIEF, ORB, BRISK or FREAK, which are binary in nature and, therefore, tend to be faster to compute and match, while requiring signicantly less memory for storage than, for example, SIFT or SURF. In this paper, we try to close this gap and present a feasibility study on the use of these descriptors for 3D face recognition. Descriptors are evaluated on the three challenging 3D face image datasets, namely, the FRGC, UMB and CASIA. Our experiments show the binary descriptors ensure slightly lower verication rates than SIFT, comparable to those of the SURF descriptor, while being an order of magnitude faster than SIFT. The results suggest that the use of binary descriptors represents a viable alternative to the established descriptors. |
2013 |
Križaj, Janez; Dobrišek, Simon; Štruc, Vitomir; Pavešić, Nikola Robust 3D face recognition using adapted statistical models Proceedings Article In: Proceedings of the Electrotechnical and Computer Science Conference (ERK'13), 2013. Abstract | Links | BibTeX | Tags: 3d face recognition, biometrics, covariance descriptor, face verification, FRGC, GMM, modeling, performance evaluation, region-covariance matrix @inproceedings{krizajrobust, The paper presents a novel framework to 3D face recognition that exploits region covariance matrices (RCMs), Gaussian mixture models (GMMs) and support vector machine (SVM) classifiers. The proposed framework first combines several 3D face representations at the feature level using RCM descriptors and then derives low-dimensional feature vectors from the computed descriptors with the unscented transform. By doing so, it enables computations in Euclidean space, and makes Gaussian mixture modeling feasible. Finally, a support vector classifier is used for identity inference. As demonstrated by our experimental results on the FRGCv2 and UMB databases, the proposed framework is highly robust and exhibits desirable characteristics such as an inherent mechanism for data fusion (through the RCMs), the ability to examine local as well as global structures of the face with the same descriptor, the ability to integrate domain-specific prior knowledge into the modeling procedure and consequently to handle missing or unreliable data. |
Štruc, Vitomir; Pavešić, Nikola; Žganec-Gros, Jerneja; Vesnicer, Boštjan Patch-wise low-dimensional probabilistic linear discriminant analysis for Face Recognition Proceedings Article In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2352–2356, IEEE 2013. Abstract | Links | BibTeX | Tags: biometrics, face verification, FRGC, ICASSP, patch-wise approach, plda, probabilistic linear discriminant analysis @inproceedings{vstruc2013patch, The paper introduces a novel approach to face recognition based on the recently proposed low-dimensional probabilistic linear discriminant analysis (LD-PLDA). The proposed approach is specifically designed for complex recognition tasks, where highly nonlinear face variations are typically encountered. Such data variations are commonly induced by changes in the external illumination conditions, viewpoint changes or expression variations and represent quite a challenge even for state-of-the-art techniques, such as LD-PLDA. To overcome this problem, we propose here a patch-wise form of the LDPLDA technique (i.e., PLD-PLDA), which relies on local image patches rather than the entire image to make inferences about the identity of the input images. The basic idea here is to decompose the complex face recognition problem into simpler problems, for which the linear nature of the LD-PLDA technique may be better suited. By doing so, several similarity scores are derived from one facial image, which are combined at the final stage using a simple sum-rule fusion scheme to arrive at a single score that can be employed for identity inference. We evaluate the proposed technique on experiment 4 of the Face Recognition Grand Challenge (FRGCv2) database with highly promising results. |