Ju Cheng Yang

Robust Finger Vein ROI Localization Based on Flexible Segmentation

Finger veins have been proved to be an effective biometric for personal identification in the recent years. However, finger vein images are easily affected by influences such as image translation, orientation, scale, scattering, finger structure, complicated background, uneven illumination, and collection posture. All these factors may contribute to inaccurate region of interest (ROI) definition, and so degrade the performance of finger vein identification system. To improve this problem, in this paper, we propose a finger vein ROI localization method that has high effectiveness and robustness against the above factors. The proposed method consists of a set of steps to localize ROIs accurately, namely segmentation, orientation correction, and ROI detection. Accurate finger region segmentation and correct calculated orientation can support each other to produce higher accuracy in localizing ROIs. Extensive experiments have been performed on the finger vein image database, MMCBNU_6000, to verify the robustness of the proposed method. The proposed method shows the segmentation accuracy of 100%. Furthermore, the average processing time of the proposed method is 22 ms for an acquired image, which satisfies the criterion of a real-time finger vein identification system.

Guided Gabor Filter for Finger Vein Pattern Extraction

In this paper, a novel explicit image filter, called Guided Gabor filter, is proposed to extract the finger vein pattern without any segmentation processing, and lower performance reduction for poor quality images which result from low contrast, illumination, or noise effects, etc. The proposed filter is contributed for finger vein enhancement, noise reduction, and haze removal without being affected by the brightness of the vein. It performs well not only on ridge detection like the Gabor filter, but on image enhancement as an edge-preserving smoothing operator without the gradient reversal artifacts. The experimental results show that the proposed method is able to get vein pattern more clearly and faster than the existing methods, and improve the matching performance with higher recognition rate.

Multimodal biometrics recognition based on local fusion visual features and variational Bayesian extreme learning machine

A new approach for multimodal biometrics recognition is proposed.Local fusion visual feature has better characterization capability.Variational Bayesian ELM provides superior performance with full Bayesian prior.Variational technology solves the automatic selection problem of hidden nodes in ELM. Multimodal biometrics provides rich information in biometric recognition systems, thus a valid multimodal feature fusion framework and an efficient recognition algorithm are desirable for multimodal biometrics systems. In this paper, we design a multimodal fusion framework for face and fingerprint images using block based feature-image matrix, and extract a type of middle-layer semantic feature from local features-a local fusion visual feature, which has better characterization capabilities with lower dimension for multimodal biometrics. Furthermore, we create recognition utilizing the Variational Bayesian Extreme Learning Machine (VBELM), which has an obvious speed advantage by random input weights, and also has superior stability and generalization by adding a non-informative full Gaussian prior. This research enables multimodal biometrics recognition system to have a concentrated fusion feature description and great recognition performance. Experimental results show that the proposed multimodal biometrics recognition system has a higher testing accuracy in comparison to the traditional methods with higher efficiency and better stability.

Intensity Variation Normalization for Finger Vein Recognition Using Guided Filter Based Singe Scale Retinex

Finger vein recognition has been considered one of the most promising biometrics for personal authentication. However, the capacities and percentages of finger tissues (e.g., bone, muscle, ligament, water, fat, etc.) vary person by person. This usually causes poor quality of finger vein images, therefore degrading the performance of finger vein recognition systems (FVRSs). In this paper, the intrinsic factors of finger tissue causing poor quality of finger vein images are analyzed, and an intensity variation (IV) normalization method using guided filter based single scale retinex (GFSSR) is proposed for finger vein image enhancement. The experimental results on two public datasets demonstrate the effectiveness of the proposed method in enhancing the image quality and finger vein recognition accuracy.

Finger Vein Recognition Using Histogram of Competitive Gabor Responses

Finger vein has been proved to be an effective biometric for personal identification in recent years. Inspired by the good power of Gabor filter in capturing specific texture characteristics from any orientation of an image, this paper proposes a simple, yet powerful and efficient local descriptor for finger vein recognition, called histogram of competitive Gabor responses (HCGR). Specially, HCGR is based on a set of competitive Gabor response (CGR) which consists of two components: competitive Gabor magnitude (CGM) and competitive Gabor orientation (CGO). A set of CGR includes the information on magnitude and orientation of the maximum responses of the Gabor filter bank with a number of different orientations. For a given image, we calculate its CGM image and CGO image and represent them in a concatenated histogram, called HCGR. This histogram can efficiently and effectively exploit the discriminative orientation and local features in a finger vein image. The experimental results obtained on our publically available finger vein image database MMCBNU_6000 demonstrate that the proposed HCGR outperforms the classical local operators such as Gabor, steerable, histogram of oriented gradients (HOG) and local binary pattern (LBP).

Finger Vein Recognition Using Generalized Local Line Binary Pattern

Finger vein images contain rich oriented features. Local line binary pattern (LLBP) is a good oriented feature representation method extended from local binary pattern (LBP), but it is limited in that it can only extract horizontal and vertical line patterns, so effective information in an image may not be exploited and fully utilized. In this paper, an orientation-selectable LLBP method, called generalized local line binary pattern (GLLBP), is proposed for finger vein recognition. GLLBP extends LLBP for line pattern extraction into any orientation. To effectually improve the matching accuracy, the soft power metric is employed to calculate the matching score. Furthermore, to fully utilize the oriented features in an image, the matching scores from the line patterns with the best discriminative ability are fused using the Hamacher rule to achieve the final matching score for the last recognition. Experimental results on our database, MMCBNU_6000, show that the proposed method performs much better than state-of-the-art algorithms that use the oriented features and local features, such as LBP, LLBP, Gabor filter, steerable filter and local direction code (LDC).

Thermal Infrared Face Recognition Based on the Modified Blood Perfusion Model and Improved Weber Local Descriptor

In order to extract the robust thermal infrared facial features, a novel method based on the modified blood perfusion model and the improved Weber local descriptor is proposed. Weber local descriptor (WLD) is able to extract a wealth of local texture information, which computes not only the differences between the center pixel and its neighbors but also the gradient orientation information describing the direction of edges in the local area, so it is suitable for texture-based thermal infrared face recognition. In order to make full use of local authentication information, an improved Weber local descriptor is proposed to extract the local features from the blood perfusion image. For improved Weber local descriptor, the Isotropic Sobel operator instead of the traditional method is used to compute the orientation and build more stable feature histograms. Experimental results show that the proposed method could achieve better recognition performance compared to the traditional methods.

Variational Bayesian extreme learning machine

Extreme learning machine (ELM) randomly generates parameters of hidden nodes and then analytically determines the output weights with fast learning speed. The ill-posed problem of parameter matrix of hidden nodes directly causes unstable performance, and the automatical selection problem of the hidden nodes is critical to holding the high efficiency of ELM. Focusing on the ill-posed problem and the automatical selection problem of the hidden nodes, this paper proposes the variational Bayesian extreme learning machine (VBELM). First, the Bayesian probabilistic model is involved into ELM, where the Bayesian prior distribution can avoid the ill-posed problem of hidden node matrix. Then, the variational approximation inference is employed in the Bayesian model to compute the posterior distribution and the independent variational hyperparameters approximately, which can be used to select the hidden nodes automatically. Theoretical analysis and experimental results elucidate that VBELM has stabler performance with more compact architectures, which presents probabilistic predictions comparison with traditional point predictions, and it also provides the hyperparameter criterion for hidden node selection.

Novel Hierarchical Structure Based Finger Vein Image Quality Assessment

Instead of existing image based and geometry based quality estimation method for finger vein image, this paper proposed a novel quality metrics from the hierarchical structure of finger vein. The thick major vessels and short minor vessels construct the hierarchical structure of finger vein, and lead to the hierarchical energy distribution. A Gaussian Energy Model is simulated to assess the hierarchical quality of the major vessel and the minor vessel respectively using Gabor filter. The efficient of matching performance and the accuracy of quality assessment are evaluated in the experimental parts.

Weber Local Gradient Pattern (WLGP) Method for Face Recognition

Robust and discriminative feature extraction without any controlled light intensity condition is vital for a real-time face recognition system. The Weber Local Descriptor (WLD) is an effective and robust face representation algorithm. However, WLD actually exploits the contrast information, which can still be sensitive to illumination changes. To overcome this problem, in this article, we take gradients into account and propose a novel operator, called Weber Local Gradient Descriptor (WLGD).This method produces the fusion characteristic and describes the facial texture through the computation of horizontal and diagonal gradients respectively. Experimental results on the ORL face database and infrared face database demonstrate that the proposed WLGD algorithm outperforms some state-of-art methods.