Robust recognition in the presence of channel variability represents one of the major research challenges in the field of automated speaker recognition. Here, the term channel variability is typically used to describe variability in the speech signal due to various (non-identity related) factors such as usage of different microphones, transmission of the speech signal over a telephone line and alike. In the scope of our R&D work on the problem of speaker recognition, we have developed a new recognition system that relies on three speech representations (i.e., MFCC, LFCC and PLP features) extracted from three frequency regions, which are used together with total variability modeling (i.e., i-vectors). To demonstrate the effectiveness of the develop system we participated in a competition on speaker recognition held in conjunction with the international conference on biometrics (ICB 2013). The competition was held on the Mobio database, which features speech recordings captured with mobile devices and hence represents a great challenge to the existing speaker recognition technology. The competition attracted 12 R&D groups from around the world (i.e., Spain, Portugal, Switzerland, Brazil, Algeria, France, the Netherlands and the Czech Republic). Despite the strong competition, our system achieved the overall best performance and won the competition.
E.02 International awards
COBISS.SI-ID: 10278996Robust facial recognition in unconstrained environments, where poor illumination, varying facial pose, low-quality images are common, still represents a major research problem that is not satisfactory solved by today's technology. In the scope of our R&D work we have developed robust facial recognition technology capable of operating in such environments. With the developed technology we took part in a face recognition competition that was organized as part of the International IAPR conference on Biometrics (ICB 2013). The competition attracted strong international competition (e.g., Idiap, Harvard, etc.) that jointly competed on the challenging Mobio database. Our system achieved the best performance among all participants and won the competition.
E.02 International awards
COBISS.SI-ID: 10176852The paper introduces a novel framework for 3D face recognition that capitalizes on region covariance descriptors and Gaussian mixture models. The framework presents an elegant and coherent way of combining multiple facial representations, while simultaneously examining all computed representations at various levels of locality. The framework first computes a number of region covariance matrices/descriptors from different sized regions of several image representations and then adopts the unscented transform to derive low-dimensional feature vectors from the computed descriptors. By doing so, it enables computations in the Euclidean space, and makes Gaussian mixture modeling feasible. In the last step a support vector machine classification scheme is used to make a decision regarding the identity of the modeled input 3D face image. The proposed framework exhibits several desirable characteristics, such as an inherent mechanism for data fusion/integration (through the region covariance matrices), the ability to examine the facial images at different levels of locality, and the ability to integrate domain-specific prior knowledge into the modeling procedure. We assess the feasibility of the proposed framework on the Face Recognition Grand Challenge version 2 (FRGCv2) database with highly encouraging results. Note that the work presented in this paper could easily be applied to other biometric (image) modalities, such as 2d face images, as well, as depth images can be considered as a form of intensity images.
B.03 Paper at an international scientific conference
COBISS.SI-ID: 9821012Similarity scores, which form the basis for identity inference in biometric verification systems, typically exhibit statistical variations. These variations are caused by so-called miss-matched conditions, in which the enrollment and probe samples were acquired, and are common to most application domains of biometric verification systems ranging from forensics to smart-home environments. To mitigate these variations, score normalization techniques are usually used. Examples of these techniques include the z-norm, the t-norm or the zt-norm. In this paper we study two-step normalization techniques, such as the zt-norm, and propose a new way of implementing such techniques. Specifically, we propose to implement the first step of the two-step procedure off-line in a non-parametric manner, while the second step is kept unchanged and, hence, performed parametrically. As shown in our face verification experiments, the proposed composite scheme can improve upon the performance of parametric normalization techniques, without an increase in computational complexity, as this is the case with pure non-parametric normalization techniques.
B.03 Paper at an international scientific conference
COBISS.SI-ID: 9757524The 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 LD-PLDA 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.
B.03 Paper at an international scientific conference
COBISS.SI-ID: 9890644