Multiple Biometric Grand Challenge Research Articles

Gender Classification through Fusion of Holistic and Region-based Facial Patterns

In this study, a robust gender prediction system is proposed to fuse global and regional facial representations through score and feature level fusion. In order to extract facial features for gender classification, Binarized Statistical Image Features (BSIF) approach is applied on holistic and regional features of face images. The extracted features are then concatenated to combine the region-based information at feature level fusion. Then the optimized sub-set of features is selected using Particle Swarm Optimization (PSO) method. Finally, the holistic and regional features are combined at score level fusion to produce the final set of scores for gender classification. This study applies Weighted Sum (WS) rule strategy for score level fusion. The experimental results are performed on Multiple Biometric Grand Challenge (MBGC) and CASIA-Iris-Distance databases with consideration of subject-disjoint training and testing evaluation to testify the validity of the proposed gender classification system. The experimental results of the study demonstrate the success of the proposed scheme for gender prediction.

An Automatic System for Unconstrained Video-Based Face Recognition

Although deep learning approaches have achieved performance surpassing humans for still image-based face recognition, unconstrained video-based face recognition is still a challenging task due to large volume of data to be processed and intra/inter-video variations on pose, illumination, occlusion, scene, blur, video quality, etc. In this work, we consider challenging scenarios for unconstrained video-based face recognition from multiple-shot videos and surveillance videos with low-quality frames. To handle these problems, we propose a robust and efficient system for unconstrained video-based face recognition, which is composed of modules for face/fiducial detection, face association, and face recognition. First, we use multi-scale single-shot face detectors to efficiently localize faces in videos. The detected faces are then grouped through carefully designed face association methods, especially for multi-shot videos. Finally, the faces are recognized by the proposed face matcher based on an unsupervised subspace learning approach and a subspace-to-subspace similarity metric. Extensive experiments on challenging video datasets, such as Multiple Biometric Grand Challenge (MBGC), Face and Ocular Challenge Series (FOCS), IARPA Janus Surveillance Video Benchmark (IJB-S) for low-quality surveillance videos and IARPA JANUS Benchmark B (IJB-B) for multiple-shot videos, demonstrate that the proposed system can accurately detect and associate faces from unconstrained videos and effectively learn robust and discriminative features for recognition.

Semi self-training beard/moustache detection and segmentation simultaneously

This paper presents a robust, fully automatic and semi self-training system to detect and segment facial beard/moustache simultaneously in challenging facial images. Based on the observation that some certain facial areas, e.g. cheeks, do not typically contain any facial hair whereas the others, e.g. brows, often contain facial hair, a self-trained model is first built using a testing image itself. To overcome the limitation of that facial hairs in brows regions and beard/moustache regions are different in length, density, color, etc., a pre-trained model is also constructed using training data. The pre-trained model is only pursued when the self-trained model produces low confident classification results. In the proposed system, we employ the superpixel together a combination of two classifiers, i.e. Random Ferns (rFerns) and Support Vector Machines (SVM) to obtain good classification performance as well as improve time efficiency. A feature vector, consisting of Histogram of Gabor (HoG) and Histogram of Oriented Gradient of Gabor (HOGG) at different directions and frequencies, is generated from both the bounding box of the superpixel and the super pixel foreground. The segmentation result is then refined by our proposed aggregately searching strategy in order to deal with inaccurate landmarking points. Experimental results have demonstrated the robustness and effectiveness of the proposed system. It is evaluated in images drawn from three entire databases i.e. the Multiple Biometric Grand Challenge (MBGC) still face database, the NIST color Facial Recognition Technology FERET database and a large subset from Pinellas County database.

Dictionary-Based Face and Person Recognition From Unconstrained Video

To recognize people in unconstrained video, one has to explore the identity information in multiple frames and the accompanying dynamic signature. These identity cues include face, body, and motion. Our approach is based on video-dictionaries for face and body. Video-dictionaries are a generalization of sparse representation and dictionaries for still images. We design the video-dictionaries to implicitly encode temporal, pose, and illumination information. In addition, our video-dictionaries are learned for both face and body, which enables the algorithm to encode both identity cues. To increase the ability of our algorithm to learn nonlinearities, we further apply kernel methods for learning the dictionaries. We demonstrate our method on the Multiple Biometric Grand Challenge, Face and Ocular Challenge Series, Honda/UCSD, and UMD data sets that consist of unconstrained video sequences. Our experimental results on these four data sets compare favorably with those published in the literature. We show that fusing face and body identity cues can improve performance over face alone.

Quality-driven and real-time iris recognition from close-up eye videos

This paper deals with the computation of robust iris templates from video sequences. The main contribution is to propose (i) optimal tracking and robust detection of the pupil, (ii) smart selection of iris images to be enrolled, and (iii) multi-thread and quality-driven decomposition of tasks to reach real-time processing. The evaluation of the system was done on the multiple biometric grand challenge dataset. Especially, we conducted a systematic study regarding the fragile bit rate and the number of merged images, using classical criteria. We reached an equal error rate value of 0.2 % that reflects high performance on this database with respect to previous studies.

SparCLeS: Dynamic <formula formulatype="inline"><tex Notation="TeX">$\ell_{1}$</tex></formula> Sparse Classifiers With Level Sets for Robust Beard/Moustache Detection and Segmentation

Robust facial hair detection and segmentation is a highly valued soft biometric attribute for carrying out forensic facial analysis. In this paper, we propose a novel and fully automatic system, called SparCLeS, for beard/moustache detection and segmentation in challenging facial images. SparCLeS uses the multiscale self-quotient (MSQ) algorithm to preprocess facial images and deal with illumination variation. Histogram of oriented gradients (HOG) features are extracted from the preprocessed images and a dynamic sparse classifier is built using these features to classify a facial region as either containing skin or facial hair. A level set based approach, which makes use of the advantages of both global and local information, is then used to segment the regions of a face containing facial hair. Experimental results demonstrate the effectiveness of our proposed system in detecting and segmenting facial hair regions in images drawn from three databases, i.e., the NIST Multiple Biometric Grand Challenge (MBGC) still face database, the NIST Color Facial Recognition Technology FERET database, and the Labeled Faces in the Wild (LFW) database.

VASIR: An Open-Source Research Platform for Advanced Iris Recognition Technologies.

The performance of iris recognition systems is frequently affected by input image quality, which in turn is vulnerable to less-than-optimal conditions due to illuminations, environments, and subject characteristics (e.g., distance, movement, face/body visibility, blinking, etc.). VASIR (Video-based Automatic System for Iris Recognition) is a state-of-the-art NIST-developed iris recognition software platform designed to systematically address these vulnerabilities. We developed VASIR as a research tool that will not only provide a reference (to assess the relative performance of alternative algorithms) for the biometrics community, but will also advance (via this new emerging iris recognition paradigm) NIST’s measurement mission. VASIR is designed to accommodate both ideal (e.g., classical still images) and less-than-ideal images (e.g., face-visible videos). VASIR has three primary modules: 1) Image Acquisition 2) Video Processing, and 3) Iris Recognition. Each module consists of several sub-components that have been optimized by use of rigorous orthogonal experiment design and analysis techniques. We evaluated VASIR performance using the MBGC (Multiple Biometric Grand Challenge) NIR (Near-Infrared) face-visible video dataset and the ICE (Iris Challenge Evaluation) 2005 still-based dataset. The results showed that even though VASIR was primarily developed and optimized for the less-constrained video case, it still achieved high verification rates for the traditional still-image case. For this reason, VASIR may be used as an effective baseline for the biometrics community to evaluate their algorithm performance, and thus serves as a valuable research platform.

Quality-Driven Super-Resolution for Less Constrained Iris Recognition at a Distance and on the Move

Less constrained iris identification systems at a distance and on the move suffer from poor resolution and poor quality of the captured iris images, which significantly degrades iris recognition performance. This paper proposes a new signal-level fusion approach which incorporates a quality score into a reconstruction-based super-resolution process to generate a high-resolution iris image from a low-resolution and quality inconsistent video sequence of an eye. A novel approach for assessing the focus level of the iris image, which is invariant to lighting and oclusion conditions, is introduced. The focus score is combined with several other quality factors to perform the quality weighted super-resolution where the highest quality frames contribute the greatest amount of information to the resulting high-resolution images without introducing spurious high-frequency components. Experiments conducted on the Multiple Biometric Grand Challenge portal dataset show that our proposed approach outperforms the traditional best quality frame selection approach and other existing state-of-the-art signal-level and score-level fusion approaches for recognition of less constrained iris at a distance and on the move.

On-line Learning of Mutually Orthogonal Subspaces for Face Recognition by Image Sets

We address the problem of face recognition by matching image sets. Each set of face images is represented by a subspace (or linear manifold) and recognition is carried out by subspace-to-subspace matching. In this paper, 1) a new discriminative method that maximises orthogonality between subspaces is proposed. The method improves the discrimination power of the subspace angle based face recognition method by maximizing the angles between different classes. 2) We propose a method for on-line updating the discriminative subspaces as a mechanism for continuously improving recognition accuracy. 3) A further enhancement called locally orthogonal subspace method is presented to maximise the orthogonality between competing classes. Experiments using 700 face image sets have shown that the proposed method outperforms relevant prior art and effectively boosts its accuracy by online learning. It is shown that the method for online learning delivers the same solution as the batch computation at far lower computational cost and the locally orthogonal method exhibits improved accuracy. We also demonstrate the merit of the proposed face recognition method on portal scenarios of multiple biometric grand challenge.

Toward the next generation of iris biometrics science

Iris biometrics involves using the pattern of texture in the iris, the colored region of the eye surrounding the pupil, to verify a person’s identity. The field originated in the work of John Daugman,1, 2 and, in recent years, heightened global and domestic security concerns have lead to an increased interest in iris biometric technology in academia, industry, and government.3 The field promises highly accurate identity verification, but a more flexible user interface is required. However, this could lead to less well-controlled image acquisition, so there is also a need for new techniques to handle a broader range of image quality. To this end, we have been supporting the US Government’s Iris Challenge Evaluation programs4 and the current Multiple Biometric Grand Challenge program,5 as well as conducting our own basic research on iris biometrics.6–8 Many factors complicate the use of iris biometrics, such as differences in pupil dilation, the presence of contact lenses, and the eye’s natural aging. Figure 1 shows an example of the type of image used. Current systems largely ignore differences in pupil dilation. They also assume that the natural aging of the eye has no effect on accuracy. Commercial technology can handle some problems that arise with contact lenses, for example, but our research suggests that there are more common, subtle, and smaller effects that are currently ignored. Iris biometrics works best when the pupil is not strongly dilated, and when the degree of dilation is similar in the image used to enroll a person in the system and the image used for verification. The conventional approach ignores differences in pupil dilation and simply converts a region from the iris image into a standard size, and then creates a corresponding binary ‘iris code‘ based on the texture pattern. In current systems of this type, pupil dilation information is discarded. Figure 1. Example iris biometrics image. The eyelids occlude the upper and lower parts of the iris. A shadow is cast on the lowest visible portion, and a specular reflection is seen at the top center of the visible portion. All of these factors complicate iris image analysis.