Constrained [formula omitted]-optimal sparse representation technique for face recognition

Multi-level dynamic error coding for face recognition with a contaminated single sample per person

Face Recognition (FR) problem is one of the significant fields in computer vision. FR is used to identify the faces that appear over distributed cameras over the network. The problem of face recognition can be divided into two categories, the first is recognition with more than one sample per person, which can be called traditional face recognition problem. The second is the recognition of faces using only a Single Sample Per Person (SSPP). The efficiency of face recognition systems decreases because of limited references especially (SSPP) and faces taken in the Operational Domain (OD) different from faces in the Enrollment Domain (ED) in illumination, pose, low-resolution, and blurriness. This paper proposed a method that deals with all problems related to face recognition with SSPP. 3D face reconstruction is used to increase the reference gallery set with different poses and generate a design domain dictionary to overcome the problem of limited reference. Besides, the design domain dictionary is used to feed different deep learning models. Face illumination transfer techniques are utilized to overcome the illumination problem. Labeled Faces in the Wild (LFW) dataset is used to train Super-Resolution Generative Adversarial Network (SRGAN) to overcome the low-resolution problem. Deblur Generative Adversarial Network (DeblurGAN) is trained on the LFW dataset to overcome the problem of blurriness. The proposed method is evaluated using the Chokepoint dataset and COX-S2V dataset. The final results confirm an overall enhancement in accuracy compared to techniques that use SSPP for face recognition (generic learning and face synthesizing approaches). Also, the proposed method outperforms of Traditional and Deep Learning (TDL) method accuracy, which uses SSPP for face recognition.

Real-world face recognition systems often have to face the single sample per person (SSPP) problem, that is, only a single training sample for each person is enrolled in the database. In this case, many of the popular face recognition methods fail to work well due to the inability to learn the discriminatory information specific to the persons to be identified. To address this problem, in this paper, we propose an Adaptive Generic Learning (AGL) method, which adapts a generic discriminant model to better distinguish the persons with single face sample. As a specific implementation of the AGL, a Coupled Linear Representation (CLR) algorithm is proposed to infer, based on the generic training set, the within-class scatter matrix and the class mean of each person given its single enrolled sample. Thus, the traditional Fisher's Linear Discriminant (FLD) can be applied to SSPP task. Experiments on the FERET and a challenging passport face database show that the proposed method can achieve better results compared with other common solutions to the SSPP problem.

The Enhanced Border Security and Visa Entry Reform Act of 2002 requires that the Visa Waiver Program be available only to countries that have a program to issue to their nationals machine-readable passports incorporating biometric identifiers complying with applicable standards established by the International Civil Aviation Organization (ICAO). In June 2002, the New Technologies Working Group of ICAO unanimously endorsed the use of face recognition (FR) as the globally interoperable biometric for machine-assisted identity confirmation with machine-readable travel documents (MRTDs), although Member States may elect to use fingerprint and/or iris recognition as additional biometric technologies. The means and formats are still being developed through which biometric information might be stored in the constrained space of integrated circuit chips embedded within travel documents. Such information will be stored in an open, yet unalterable and very compact format, probably as digitally signed and efficiently compressed images. The objective of this research is to characterize the many factors that affect FR system performance with respect to the legislated mandates concerning FR. A photograph acquisition environment and a commercial face recognition system have been installed at Mitretek, and over 1,400 images have been collected of volunteers. The image database and FR system are being used to analyze the effects of lossy image compression, individual differences, such as eyeglasses and facial hair, and the acquisition environment on FR system performance. Images are compressed by varying ratios using JPEG2000 to determine the trade-off points between recognition accuracy and compression ratio. The various acquisition factors that contribute to differences in FR system performance among individuals are also being measured. The results of this study will be used to refine and test efficient face image interchange standards that ensure highly accurate recognition, both for automated FR systems and human inspectors. Working within the M1-Biometrics Technical Committee of the InterNational Committee for Information Technology Standards (INCITS) organization, a standard face image format will be tested and submitted to organizations such as ICAO.

Due to the absence of samples with intra-class variation, extracting discriminative facial features and building powerful classifiers are the bottlenecks of improving the performance of face recognition (FR) with single sample per person (SSPP). In this paper, we propose to learn regional adaptive convolution features which are locally and globally discriminative to face identity and robust to face variation. With collected generic facial variations, a novel class-level joint representation framework is presented to exploit the distinctiveness and class-level commonality of different facial features. In the proposed class-level joint representation with regional adaptive convolution feature (CJR-RACF), both discriminative facial features robust to various facial variations and powerful representation for classification with generic facial variations that can overcome the small-sample-size problem are fully exploited. CJR-RACF has been evaluated on several popular databases, including large-scale CMU Multi-PIE and LFW databases. Experimental results demonstrate the much higher robustness and effectiveness of CJR-RACF to complex facial variations compared to the state-of-the-art methods.

In recent years, the performances of face recognition have been improved significantly by using convolution neural networks (CNN) as the feature extractors. On the other hands, in order to avoid spreading COVID-19 virus, people would wear mask even when they want to pass the face recognition system. Thus, it is necessary to improve the performance of masked face recognition so that users could utilize face recognition methods more easily. In this paper, we propose a feature extraction backbone named ResSaNet that integrates CNN (especially Residual block) and Self-attention module into the same network. By capturing the local and global information of face area simultaneously, our proposed ResSaNet could achieve promising results on both masked and non-masked testing data.

Face recognition at a distance is one grand challenge for security surveillance. In this paper, the face images at different distances are simulated by varying image scales (resolutions). The performances of three face recognition algorithms (matchers) are tested with variant image scales (simulating different distances) and with two spectral images (modalities). The three selected matchers are face pattern byte, elastic bunch graph matching, and linear discriminant analysis; while the two modalities are visible and thermal images. The performance of a face recognition system can be measured by accuracy (AC) rate and false accept rate (FAR). To enhance the performance of face recognition especially at a distance, score fusion techniques are applied, which combine several scores from multiple matchers and multiple modalities. Our experiments are conducted with the ASUMS face dataset consisting of two spectral images (visible and thermal) from 135 subjects. The experimental results show that the face recognition with small image scales (simulating long distances) have low performance (e.g., AC=91.36%, FAR=8.64% for 20×20-pixel images); and score fusion can greatly improve accuracy (99.34%) meanwhile reduce FAR (0.31%).

In face recognition, face rotation alignment is an important part of the recognition process. In this paper, we present a hierarchical detector system using eye and eye-pair detectors combined with a geometrical method for calculating the in-plane angle of a face image. Two feature extraction methods, the restricted Boltzmann machine and the histogram of oriented gradients, are compared to extract feature vectors from a sliding window. Then a support vector machine is used to accurately localize the eyes. After the eye coordinates are obtained through our eye detector, the in-plane angle is estimated by calculating the arc-tangent of horizontal and vertical parts of the distance between left and right eye center points. By using this calculated in-plane angle, the face is subsequently rotationally aligned. We tested our approach on three different face datasets: IMM, Labeled Faces in the Wild (LFW) and FERET. Moreover, to compare the effect of rotational aligning on face recognition performance, we performed experiments using a face recognition method using rotationally aligned and non-aligned face images from the IMM dataset. The results show that our method calculates the in-plane rotation angle with high precision and this leads to a significant gain in face recognition performance.

Face detection by low-resolution image (LR) is one of the key aspects of Human-Computer Interaction(HCI). Due to the LR image, which has changes in pose, lighting, and illumination, the performance of face recognition is reduced. In this work, we propose the Deep Belief Network-Crossover based Firefly (DBN-CROFF) method for face recognition from low-resolution images. The Histogram of Gradient (HOG) and 2-Dimensional Discrete Wavelet Transform (2D-DWT) to extract facial width, size of the cheeks, skin tone, nose, and lip shape features from facial data. The Kernel Principle Component Analysis (k-PCA) is used to successfully reduce the dimension of the feature. The experimental performance of the proposed method is evaluated using four datasets namely LFW, Multi-PIE, Extended Yale-B, and FERET with conventional techniques. Finally, the proposed DBN-CROFF solution surpasses the other conventional facial recognition approaches by giving a higher accuracy of recognization.

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.

In this paper, a novel approach for illumination normalization under varying lighting conditions is presented. Our approach utilizes the fact that discrete cosine transform (DCT) low-frequency coefficients correspond to illumination variations in a digital image. Under varying illuminations, the images captured may have low contrast; initially we apply histogram equalization on these for contrast stretching. Then the low-frequency DCT coefficients are scaled down to compensate the illumination variations. The value of scaling down factor and the number of low-frequency DCT coefficients, which are to be re-scaled, are obtained experimentally. The classification is done using k-nearest neighbor classification and nearest mean classification on the images obtained by inverse DCT on the processed coefficients. The correlation coefficient and Euclidean distance obtained using principal component analysis are used as distance metrics in classification. We have tested our face recognition method using Yale face database B. The results show that our method performs without any error (100% face recognition performance) even on the most extreme illumination variations. There are different schemes in the literature for illumination normalization under varying lighting conditions, but no one is claimed to give 100% recognition rate under all illumination variations for this database. The proposed technique is computationally efficient and can easily be implemented for real time face recognition system.

This paper describes an approach of human sensing using multi-view image patterns. In particular we will focus on a robust face recognition among various information obtained through human sensing. Since our face recognition method is based on the similarity between the distributions of multi-view face images, how to gather such face images is a key issue to achieve high performance. In order to realize stable gathering face images, we introduce a multi-camera system with six IEEE 13 94 PC cameras installed around the frame of a monitor. We confirmed that the performance of face recognition is improved largely by using the multi-camera system in comparison to a single camera system through experimental results.

The literature on independent component analysis (ICA)-based face recognition generally evaluates its performance using standard principal component analysis (PCA) within two architectures, ICA Architecture I and ICA Architecture II. In this correspondence, we analyze these two ICA architectures and find that ICA Architecture I involves a vertically centered PCA process (PCA I), while ICA Architecture II involves a whitened horizontally centered PCA process (PCA II). Thus, it makes sense to use these two PCA versions as baselines to reevaluate the performance of ICA-based face-recognition systems. Experiments on the FERET, AR, and AT&T face-image databases showed no significant differences between ICA Architecture I (II) and PCA I (II), although ICA Architecture I (or II) may, in some cases, significantly outperform standard PCA. It can be concluded that the performance of ICA strongly depends on the PCA process that it involves. Pure ICA projection has only a trivial effect on performance in face recognition.

Most face recognition methods employ single-bit binary descriptors for face representation. The information from these methods is lost in the process of quantization from real-valued descriptors to binary descriptors, which greatly limits their robustness for face recognition. In this study, we propose a novel weighted feature histogram (WFH) method of multi-scale local patches using multi-bit binary descriptors for face recognition. First, to obtain multi-scale information of the face image, the local patches are extracted using a multi-scale local patch generation (MSLPG) method. Second, with the goal of reducing the quantization information loss of binary descriptors, a novel multi-bit local binary descriptor learning (MBLBDL) method is proposed to extract multi-bit local binary descriptors (MBLBDs). In MBLBDL, a learned mapping matrix and novel multi-bit coding rules are employed to project pixel difference vectors (PDVs) into the MBLBDs in each local patch. Finally, a novel robust weight learning (RWL) method is proposed to learn a set of robust weights for each patch to integrate the MBLBDs into the final face representation. In RWL, a codebook is first constructed by clustering MBLBDs on each local patch to extract a feature histogram. Then, considering that different parts of the face have different degrees of robustness to local changes, a set of weights is learned to concatenate the feature histograms of all local patches into the final representation of a face image. In addition, to further improve the performance for heterogeneous face recognition, a coupled WFH (C-WFH) method is proposed. C-WFH maintains the similarity of the corresponding MBLBDs and feature histograms for a pair of heterogeneous face images by means of a novel coupled feature learning (CFL) method to reduce the modality gap. A series of experiments are conducted on widely used face datasets to analyze the performance of WFH and C-WFH. Extensive experimental results show that WFH and C-WFH outperform state-of-the-art face recognition methods.

Lack of training samples always affects the performance and robustness of face recognition. Generating virtual samples is one of effective methods to expand the training set. When the virtual samples are able to simulate the variations of facial images including variations of illuminations, facial postures and the facial expressions, the robustness will be enhanced and the accuracy will be improved obviously in the face recognition problem. In this paper, an improved linear representation-based classification combined virtual samples (ILRCVS) is proposed. First, we design a new objective function that simultaneously considers the information of the virtual training samples and the virtual test sample. Second, an alternating minimization algorithm is proposed to solve the optimization problem of the objective function. Finally, a new classification criterion combined with the virtual training and test sample is proposed. Experimental results on the Georgia Tech, FERET and Yale B face databases show that the proposed method is more robust than three state-of-the-art face recognition methods, LRC, SRC and CRC.