Enhanced Local Gradient Order Features and Discriminant Analysis for Face Recognition

Probabilistic Linear Discriminant Analysis Based on L1-Norm and Its Bayesian Variational Inference

Probabilistic linear discriminant analysis (PLDA) is a very effective feature extraction approach and has obtained extensive and successful applications in supervised learning tasks. It employs the squared L₂ -norm to measure the model errors, which assumes a Gaussian noise distribution implicitly. However, the noise in real-life applications may not follow a Gaussian distribution. Particularly, the squared L₂ -norm could extremely exaggerate data outliers. To address this issue, this article proposes a robust PLDA model under the assumption of a Laplacian noise distribution, called L1-PLDA. The learning process employs the approach by expressing the Laplacian density function as a superposition of an infinite number of Gaussian distributions via introducing a new latent variable and then adopts the variational expectation-maximization (EM) algorithm to learn parameters. The most significant advantage of the new model is that the introduced latent variable can be used to detect data outliers. The experiments on several public databases show the superiority of the proposed L1-PLDA model in terms of classification and outlier detection.

A New Face Image Recognition Algorithm Based on Cerebellum-Basal Ganglia Mechanism

Face recognition is one of the popular areas of research in the field of computer vision. It is mainly used for identification and security system. One of the major challenges in face recognition is identification under numerous illumination environments by changing the direction of light or modifying the lighting magnitude. Exacting illumination invariant features is an effective approach to solve this problem. Conventional face recognition algorithms based on nonsubsampled contourlet transform (NSCT) and bionic mode are not capable enough to recognize the similar faces with great accuracy. Hence, in this paper, an attempt is made to propose an enhanced cerebellum-basal ganglia mechanism (CBGM) for face recognition. The integral projection and geometric feature assortment method are used to acquire the facial image features. The cognition model is deployed which is based on the cerebellum-basal ganglia mechanism and is applied for extraction of features from the face image to achieve greater accuracy for recognition of face images. The experimental results reveal that the enhanced CBGM algorithm can effectively recognize face images with greater accuracy. The recognition rate of 100 AR face images has been found to be 96.9%. The high recognition accuracy rate has been achieved by the proposed CBGM technique.

Learning Kernel for Conditional Moment-Matching Discrepancy-Based Image Classification

Conditional maximum mean discrepancy (CMMD) can capture the discrepancy between conditional distributions by drawing support from nonlinear kernel functions; thus, it has been successfully used for pattern classification. However, CMMD does not work well on complex distributions, especially when the kernel function fails to correctly characterize the difference between intraclass similarity and interclass similarity. In this paper, a new kernel learning method is proposed to improve the discrimination performance of CMMD. It can be operated with deep network features iteratively and thus denoted as KLN for abbreviation. The CMMD loss and an autoencoder (AE) are used to learn an injective function. By considering the compound kernel, that is, the injective function with a characteristic kernel, the effectiveness of CMMD for data category description is enhanced. KLN can simultaneously learn a more expressive kernel and label prediction distribution; thus, it can be used to improve the classification performance in both supervised and semisupervised learning scenarios. In particular, the kernel-based similarities are iteratively learned on the deep network features, and the algorithm can be implemented in an end-to-end manner. Extensive experiments are conducted on four benchmark datasets, including MNIST, SVHN, CIFAR-10, and CIFAR-100. The results indicate that KLN achieves the state-of-the-art classification performance.

Discriminative Residual Analysis for Image Set Classification with Posture and Age Variations

Image set recognition has been widely applied in many practical problems like real-time video retrieval and image caption tasks. Due to its superior performance, it has grown into a significant topic in recent years. However, images with complicated variations, e.g., postures and human ages, are difficult to address, as these variations are continuous and gradual with respect to image appearance. Consequently, the crucial point of image set recognition is to mine the intrinsic connection or structural information from the image batches with variations. In this work, a Discriminant Residual Analysis (DRA) method is proposed to improve the classification performance by discovering discriminant features in related and unrelated groups. Specifically, DRA attempts to obtain a powerful projection which casts the residual representations into a discriminant subspace. Such a projection subspace is expected to magnify the useful information of the input space as much as possible, then the relation between the training set and the test set described by the given metric or distance will be more precise in the discriminant subspace. We also propose a nonfeasance strategy by defining another approach to construct the unrelated groups, which help to reduce furthermore the cost of sampling errors. Two regularization approaches are used to deal with the probable small sample size problem. Extensive experiments are conducted on benchmark databases, and the results show superiority and efficiency of the new methods.

Probabilistic Linear Discriminant Analysis With Vectorial Representation for Tensor Data

Linear discriminant analysis (LDA) has been a widely used supervised feature extraction and dimension reduction method in pattern recognition and data analysis. However, facing high-order tensor data, the traditional LDA-based methods take two strategies. One is vectorizing original data as the first step. The process of vectorization will destroy the structure of high-order data and result in high dimensionality issue. Another is tensor LDA-based algorithms that extract features from each mode of high-order data and the obtained representations are also high-order tensor. This paper proposes a new probabilistic LDA (PLDA) model for tensorial data, namely, tensor PLDA. In this model, each tensorial data are decomposed into three parts: the shared subspace component, the individual subspace component, and the noise part. Furthermore, the first two parts are modeled by a linear combination of latent tensor bases, and the noise component is assumed to follow a multivariate Gaussian distribution. Model learning is conducted through a Bayesian inference process. To further reduce the total number of model parameters, the tensor bases are assumed to have tensor CandeComp/PARAFAC (CP) decomposition. Two types of experiments, data reconstruction and classification, are conducted to evaluate the performance of the proposed model with the convincing result, which is superior or comparable against the existing LDA-based methods.

Analysis of a robust edge detection system in different color spaces using color and depth images

Edge detection is very important technique to reveal significant areas in the digital image, which could aids the feature extraction techniques. In fact it is possible to remove un-necessary parts from image, using edge detection. A lot of edge detection techniques has been made already, but we propose a robust evolutionary based system to extract the vital parts of the image. System is based on a lot of pre and post-processing techniques such as filters and morphological operations, and applying modified Ant Colony Optimization edge detection method to the image. The main goal is to test the system on different color spaces, and calculate the system’s performance. Another novel aspect of the research is using depth images along with color ones, which depth data is acquired by Kinect V.2 in validation part, to understand edge detection concept better in depth data. System is going to be tested with 10 benchmark test images for color and 5 images for depth format, and validate using 7 Image Quality Assessment factors such as Peak Signal-to-Noise Ratio, Mean Squared Error, Structural Similarity and more (mostly related to edges) for prove, in different color spaces and compared with other famous edge detection methods in same condition. Also for evaluating the robustness of the system, some types of noises such as Gaussian, Salt and pepper, Poisson and Speckle are added to images, to shows proposed system power in any condition. The goal is reaching to best edges possible and to do this, more computation is needed, which increases run time computation just a bit more. But with today’s systems this time is decreased to minimum, which is worth it to make such a system. Acquired results are so promising and satisfactory in compare with other methods available in validation section of the paper.

Fuzzy Sparse Autoencoder Framework for Single Image Per Person Face Recognition

The issue of single sample per person (SSPP) face recognition has attracted more and more attention in recent years. Patch/local-based algorithm is one of the most popular categories to address the issue, as patch/local features are robust to face image variations. However, the global discriminative information is ignored in patch/local-based algorithm, which is crucial to recognize the nondiscriminative region of face images. To make the best of the advantage of both local information and global information, a novel two-layer local-to-global feature learning framework is proposed to address SSPP face recognition. In the first layer, the objective-oriented local features are learned by a patch-based fuzzy rough set feature selection strategy. The obtained local features are not only robust to the image variations, but also usable to preserve the discrimination ability of original patches. Global structural information is extracted from local features by a sparse autoencoder in the second layer, which reduces the negative effect of nondiscriminative regions. Besides, the proposed framework is a shallow network, which avoids the over-fitting caused by using multilayer network to address SSPP problem. The experimental results have shown that the proposed local-to-global feature learning framework can achieve superior performance than other state-of-the-art feature learning algorithms for SSPP face recognition.

Fractional Wavelet Scattering Network and Applications

OBJECTIVE

This study introduces a fractional wavelet scattering network (FrScatNet), which is a generalized translation invariant version of the classical wavelet scattering network.

METHODS

In our approach, the FrScatNet is constructed based on the fractional wavelet transform (FRWT). The fractional scattering coefficients are iteratively computed using FRWTs and modulus operators. The feature vectors constructed by fractional scattering coefficients are usually used for signal classification. In this paper, an application example of the FrScatNet is provided in order to assess its performance on pathological images. First, the FrScatNet extracts feature vectors from patches of the original histological images under different orders. Then we classify those patches into target (benign or malignant) and background groups. And the FrScatNet property is analyzed by comparing error rates computed from different fractional orders, respectively. Based on the above pathological image classification, a gland segmentation algorithm is proposed by combining the boundary information and the gland location.

RESULTS

The error rates for different fractional orders of FrScatNet are examined and show that the classification accuracy is improved in fractional scattering domain. We also compare the FrScatNet-based gland segmentation method with those proposed in the 2015 MICCAI Gland Segmentation Challenge and our method achieves comparable results.

CONCLUSION

The FrScatNet is shown to achieve accurate and robust results. More stable and discriminative fractional scattering coefficients are obtained by the FrScatNet in this paper.

SIGNIFICANCE

The added fractional order parameter is able to analyze the image in the fractional scattering domain.

Kernel Embedding Multiorientation Local Pattern for Image Representation

Local feature descriptor plays a key role in different image classification applications. Some of these methods such as local binary pattern and image gradient orientations have been proven effective to some extent. However, such traditional descriptors which only utilize single-type features, are deficient to capture the edges and orientations information and intrinsic structure information of images. In this paper, we propose a kernel embedding multiorientation local pattern (MOLP) to address this problem. For a given image, it is first transformed by gradient operators in local regions, which generate multiorientation gradient images containing edges and orientations information of different directions. Then the histogram feature which takes into account the sign component and magnitude component, is extracted to form the refined feature from each orientation gradient image. The refined feature captures more information of the intrinsic structure, and is effective for image representation and classification. Finally, the multiorientation refined features are automatically fused in the kernel embedding discriminant subspace learning model. The extensive experiments on various image classification tasks, such as face recognition, texture classification, object categorization, and palmprint recognition show that MOLP could achieve competitive performance with those state-of-the art methods.

Pairwise Identity Verification via Linear Concentrative Metric Learning

This paper presents a study of metric learning systems on pairwise identity verification, including pairwise face verification and pairwise speaker verification, respectively. These problems are challenging because the individuals in training and testing are mutually exclusive, and also due to the probable setting of limited training data. For such pairwise verification problems, we present a general framework of metric learning systems and employ the stochastic gradient descent algorithm as the optimization solution. We have studied both similarity metric learning and distance metric learning systems, of either a linear or shallow nonlinear model under both restricted and unrestricted training settings. Extensive experiments demonstrate that with limited training pairs, learning a linear system on similar pairs only is preferable due to its simplicity and superiority, i.e., it generally achieves competitive performance on both the labeled faces in the wild face dataset and the NIST speaker dataset. It is also found that a pretrained deep nonlinear model helps to improve the face verification results significantly.

Class-Specific Kernel Discriminant Analysis Revisited: Further Analysis and Extensions

In this paper, we revisit class-specific kernel discriminant analysis (KDA) formulation, which has been applied in various problems, such as human face verification and human action recognition. We show that the original optimization problem solved for the determination of class-specific discriminant projections is equivalent to a low-rank kernel regression (LRKR) problem using training data-independent target vectors. In addition, we show that the regularized version of class-specific KDA is equivalent to a regularized LRKR problem, exploiting the same targets. This analysis allows us to devise a novel fast solution. Furthermore, we devise novel incremental, approximate and deep (hierarchical) variants. The proposed methods are tested in human facial image and action video verification problems, where their effectiveness and efficiency is shown.

Largest Matching Areas for Illumination and Occlusion Robust Face Recognition

In this paper, we introduce a novel approach to face recognition which simultaneously tackles three combined challenges: (1) uneven illumination; (2) partial occlusion; and (3) limited training data. The new approach performs lighting normalization, occlusion de-emphasis and finally face recognition, based on finding the largest matching area (LMA) at each point on the face, as opposed to traditional fixed-size local areabased approaches. Robustness is achieved with novel approaches for feature extraction, LMA-based face image comparison and unseen data modeling. On the extended YaleB and AR face databases for face identification, our method using only a single training image per person, outperforms other methods using a single training image, and matches or exceeds methods which require multiple training images. On the labeled faces in the wild face verification database, our method outperforms comparable unsupervised methods. We also show that the new method performs competitively even when the training images are corrupted.