Yarui Chen

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.

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.

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.

Multimodal Biometrics Recognition Based on Image Latent Semantic Analysis and Extreme Learning Machine

Multimodal biometrics recognition system suffers from the shortcomings of large data processing and much time cost during the recognition. To overcome the shortcomings of the traditional methods, in this paper, a novel multimodal biometrics recognition method is proposed by using image latent semantic analysis and extreme learning machine method. The image latent semantic analysis for multimodal biometrics feature extraction will extract abandon information from the images and the extreme learning machine method has the merits of high accuracy and fast speed. With this new method, the latent semantic features from the multimodal biometrics images are digged out to improve the recognition accuracy. Finally, the extreme learning machine is used as the classifier. The experiments show that the proposed algorithm has get better performances both in recognition accuracy and speed.

A Novel Multimodal Biometrics Recognition Model Based on Stacked ELM and CCA Methods

Multimodal biometrics combine a variety of biological features to have a significant impact on identification performance, which is a newly developed trend in biometrics identification technology. This study proposes a novel multimodal biometrics recognition model based on the stacked extreme learning machines (ELMs) and canonical correlation analysis (CCA) methods. The model, which has a symmetric structure, is found to have high potential for multimodal biometrics. The model works as follows. First, it learns the hidden-layer representation of biological images using extreme learning machines layer by layer. Second, the canonical correlation analysis method is applied to map the representation to a feature space, which is used to reconstruct the multimodal image feature representation. Third, the reconstructed features are used as the input of a classifier for supervised training and output. To verify the validity and efficiency of the method, we adopt it for new hybrid datasets obtained from typical face image datasets and finger-vein image datasets. Our experimental results demonstrate that our model performs better than traditional methods.

Face recognition based on 4 Dimensions Local Binary Patterns

In face recognition, LBP (Local Binary Patterns) is a very popular method, which can solve the defects of the traditional local feature extraction methods with fixed scale and small extraction scale. However, the LBP operator only describes the relationship between the center pixel and its neighborhood pixels, it ignores the relationship among the operators. 3DLBP (3 Dimensions Local Binary Patterns) operator embodies this relationship to get a better local description. However, both of them neglect the center pixel value, which also reflects some properties of the image points. In this paper, we propose a novel face recognition method based on 4DLBP (4 Dimensions Local Binary Patterns), which adds the pixel value of the center point into the 3DLBP features for face recognition. We firstly partition the face image into small blocks, and then we extract the 4DLBP features of the blocked images, and combine the features to obtain the final facial features. Finally, we use the extreme learning machine (ELM) as classifier to train and classify the face images. The experimental results show the proposed method has better performances than the traditional methods.

A Liveness Detection Method Based on Blood Volume Pulse Probing

In this paper, we propose a novel method of detecting live body samples in biometrics, which is based on the detection of a blood volume pulse. We used an auto-encoder to extract a signal from the video captured from skin to determine whether the sample is alive or not. The experimental results confirmed that our method could accurately distinguish between live body samples and spoofed samples.

Image latent semantic analysis based face recognition with ensemble extreme learning machine

To overcome the shortcomings of the traditional methods, this paper proposes a novel face recognition method based on the image latent semantic features and ensemble extreme learning machine. The image latent semantic analysis is to acquire the high-level features from the face image, which has good robustness to illumination and expression changes. The image latent features are extracted as fellows: firstly, we obtain the low-level features of face image by the feature extraction methods of Gabor filter, local ternary pattern (LTP), and invariant moments. Then, we build the feature-image matrix based on the low-level features, and decompose the matrix with two dimension matrix decomposition to get the image latent semantic features. Finally, the ensemble extreme learning machine is used to classify the latent semantic features, which combines lots of extreme learning machine to obtain a stable classifier. The experimental results show that our proposed algorithm is more effective when compared with other algorithms.