Field Of Face Recognition Research Articles

Eye localization based on weight binarization cascade convolution neural network

Eye localization is a key step in the field of face recognition and analysis, which is the premise and breakthrough of drowsiness estimation and auxiliary driving. An eye localization method based on Weight Binarization Cascade Convolution Neural Network (WBCCNN) is proposed, in which the WBCCNN is composed of four levels and the weight is constrained by binarization. It predicts eye positions from coarse-to-fine to improve the performance of eye localization, and binary network not only helps to reduce the storage size of the model, but also speeds up the operation. Experiments on eye localization are performed using Labeled Faces in the Wild (LFW), BioID, and Labeled Face Parts in the Wild (LFPW) Databases, from which the results show that the average detection errors of left eye and right eye by our method are 0.66% and 0.71% on LFW, respectively. The operation speed of binary network is approximately as twice as that of non-binary. In addition, our method requires less storage capacity, which maintains higher performance on BioID and LFPW, compared to some state-of-the-art works.

Convolutional Approach Also Benefits Traditional Face Pattern Recognition Algorithm [208!

Convolutional neural networks (CNN) are widely used deep learning frameworks and are applied in the field of face recognition, achieving outstanding results. The Macropixel comparison approach is a shallow mathematical approach that recognizes faces by comparing the original pixel blocks of face images. In this article, the authors are inspired by ideas of the currently popular deep neural network framework and introduce two features into the mathematical approach: deep overlap and weighted filter. The aim is to explore if the idea of deep learning could benefit mathematical recognition method, which might extend the scope of face recognition research. Results from the experiments show that the new proposed approach achieves markedly better recognition rates than the original macropixel methods.

Assessment Of Color Normalization Algorithms Under Various Illuminations

Contrast enrichment is an essential area in the field of digital image handling for human visual perception and computer vision. Digital images have become a part of our everyday life and imaging devices are everywhere, from higher end digital cameras to video cameras integrated in laptops or cell phones. Images of a scenery taken with a number of cameras will possess diverse values of color owing to the deviations in reproducing color through various devices. Humans are likely to neglect the illumination while adjudicating the appearance of an entity. However the same does not hold true for various image capturing devices where the same object will often look different under different illuminations. The goal of the computational color normalization is to account for the result of the illuminate. This paper aims at simulating and comparing few of the color normalization algorithms like Histogram Equalization, Gamma correction and White patch Retinex using MATLAB image processing toolbox and a few statistical parameters related to the processed image are found. The results indicated that the retinex algorithm performed better than the other algorithms and it could be a prospective area of research in the field of face recognition.

Research on Application of Face Recognition Techniques in Social Networks

The progress in information technology makes social networks much more compact between people from all over the world. In the age of Internet, many new social interaction ways become more and more prevalent such as instant messaging, Web conference. These tools help people share their ideas and cooperate. However, in the meantime, there exist some risks because the person you are chatting with may just be a fake one. In this situation, the face recognition techniques could help identify the truth and make the social networks safe. In this paper, research is conducted on application of face recognition techniques into daily social networks. By combining robust face recognition techniques into our social networks, we can better discriminate risks on the Internet and make full use of social networks on academics, business or other issues. At first, the basic concept of social networks is introduced. Afterwards, the state of the art in the field of face recognition is described. Finally, some suggested ways are given on how to apply face recognition techniques into our social networks.

An Improved Two-Step Face Recognition Algorithm Based on Sparse Representation

Weighted score fusion is a widely used score fusion scheme, but the weights need to be set manually. The results generally vary greatly when the weights are different, so it is difficult to find the optimal weights. This is why it is necessary to constantly set different weights for experimental comparisons to find the optimal weights. In this paper, an improved fusion method is proposed for above shortcoming, that is, multiplication fusion applicable to sparse representation. The fusion scheme not only is easy to use but also does not need to be artificially set weights. Moreover, it is consistent with the correlation between the classification error and the score obtained by the experimental analysis. In the field of face recognition, it has been shown that the two-step face recognition (TSFR) based on representation using the original training samples and the generated “symmetric face” training samples can achieve excellent face recognition performance. Face recognition based on multiplication fusion and TSFR proposed in this paper can further improve the recognition accuracy.

Maximal Uncorrelated Multinomial Logistic Regression

Multinomial logistic regression (MLR) has been widely used in the field of face recognition, text classification, and so on. However, the standard multinomial logistic regression has not yet stressed the problem of data redundancy. That is to say, in multi-class classification, there are many similar features among different classes, which will cause the corresponding classes not being correctly classified. As data redundancy is a common phenomenon in many fields, in response to this phenomenon, this paper proposes a maximal uncorrelated MLR (MUMLR) classification model to solve the problem of data redundancy in multi-class classification. The main idea is to reduce the weight of similar features and try to keep more discriminative information in the data by adding an uncorrelated regularization. In addition, we use the Cauchy-Buniakowsky-Schwarz inequation to scale the original objective function into the convex function and solve it by the Adam optimization method. Its main advantages are as follows: for data with more redundant information, the classification effect of the proposed algorithm is better than the state-of-the-art algorithms. In addition, we prove that the regularization we proposed can also be applied to neural networks and has achieved good results.

Impact and Detection of Facial Beautification in Face Recognition: An Overview

Facial beautification induced by plastic surgery, cosmetics or retouching has the ability to substantially alter the appearance of face images. Such types of beautification can negatively affect the accuracy of face recognition systems. In this work, a conceptual categorisation of beautification is presented, relevant scenarios with respect to face recognition are discussed, and related publications are revisited. Additionally, technical considerations and trade-offs of the surveyed methods are summarized along with open issues and challenges in the field. This survey is targeted to provide a comprehensive point of reference for biometric researchers and practitioners working in the field of face recognition, who aim at tackling challenges caused by facial beautification.

Self Residual Attention Network for Deep Face Recognition

Discriminative feature embedding is of essential importance in the field of large scale face recognition. In this paper, we propose a self residual attention-based convolutional neural network (SRANet) for discriminative face feature embedding, which aims to learn the long-range dependencies of face images by decreasing the information redundancy among channels and focusing on the most informative components of spatial feature maps. More specifically, the proposed attention module consists of the self channel attention (SCA) block and self spatial attention (SSA) block which adaptively aggregates the feature maps in both channel and spatial domains to learn the inter-channel relationship matrix and the inter-spatial relationship matrix; moreover, matrix multiplications are conducted for a refined and robust face feature. With the attention module we proposed, we can make standard convolutional neural networks (CNNs), such as ResNet-50 and ResNet-101, which have more discriminative power for deep face recognition. The experiments on Labelled Faces in the Wild (LFW), Age Database (AgeDB), Celebrities in Frontal Profile (CFP), and MegaFace Challenge 1 (MF1) show that our proposed SRANet structure consistently outperforms naive CNNs and achieves state-of-the-art performance.

Vocabulary Trees with OSS Detectors

In today’s diversified world, with every person having their own idiosyncratic identity, the field of face detection and recognition has received significant scope. Since birth, humans develop and harvest similar facial features, making their recognition a challenging problem. Thus, the development of faster, more accurate and robust algorithms is of prime importance.The most critical requirements in developing a reliable face recognition algorithm is a large database of facial images and a well-developed systematic procedure to evaluate the system. In this paper, we bring out an approach to implement quick facial recognition using the concept of vocabulary trees in accordance with ORB, SIFT and SURF detectors and compare their performance. The model is trained using the Grimace, Face95 and ORL databases. The experiments are conducted by employing various state-of-the-art clustering algorithms and the results are compared for accuracy. The results and comparisons obtained on the databases show that the ORB detector clustered using Spectral clustering algorithm to construct the Vocabulary Tree outperforms the other techniques.

Improving sparse representation-based image classification using truncated total least squares

In the field of face recognition, the Sparse Representation-based Classification (SRC) method can effectively deal with many common problems such as face occlusion, lighting and expression changes. Truncated Total Least Squares (TTLS) method is determined by using an optimal cutoff factor k. The choice of truncation factor regularization parameters directly affects the quality of the solution. The truncation of total least squares is suitable for solving the linear problems of the same kind. According to this motivation, a classification method TSRC based on the truncation representation is proposed. The truncated global least squares regularization is fused with sparse representation to optimize the representation coefficients. We performed a large number of experiments with this method on several popular benchmark datasets, and the results showed that the sparse representation can be improved if it is combined with the truncation. In most cases, the proposed truncation-based classification method has higher classification accuracy.

Extended interval type-II and kernel based sparse representation method for face recognition

• Unseen information is extracted using extended interval type 2 membership function. • It also works where other Gaussian based membership functions are not applicable. • Computational efficient: using sparsity concept which makes FR systems fast. • It deals with uncertainty originating from non-linear variations in the features. • It gives better results as compared to other state-of-art methods. In the world of ubiquitous computing, fuzzy logic has been emerged as an important research area in the field of face recognition (FR) applications. In this paper, a new efficient and advanced method; inspired from interval type-II fuzzy membership concept of fuzzy logic is proposed. The motivation behind our method is to exploit the benefit of an extended interval type-II membership function: a new concept to fuzzy logics; in collaboration with kernel based sparse representation for FR. To integrate all the pluton, we propose a method called: extended interval type-II and kernel based sparse representation method (ExIntTy2KBSRM). In our proposed method, first we figure out the measure of participation of individual pixels in identifying face images using a variant of Interval type-II fuzzy logic i.e. extended interval type-II membership function in place of type 1 fuzzy logic. Next, we calculate K nearest neighbor to training specimens using simple Euclidean distance metric for sparse representation of each test specimen as a combinatorial of calculated K nearest training specimens. After this, we do classification based on contribution made by calculated train specimens in representation results. The efficacy and effectiveness of our proposed method is shown based on experiments performed on various standard databases. The experimental results show that our method deal with challenges of face recognition more efficiently as compared to other state of art methods, as it integrates the pluton of two different membership function based extended interval type-II fuzzy logics in collaboration with kernel sparse representation. Also, our experimental analysis tells that our proposed method improves the classification accuracy to 2–10% greater than the other existing relevant methods. Impact and significance of the proposed method: The main impact of the proposed method in FR based expert and intelligent systems is that, it considers unseen information available in pixel values of a face image present due to non-linear variations and overlapping of pixels. It also contains the advantage of spatial similar structure information present in face images. This makes the system more effective and efficient in processing face images for FR. Our method also works where Gaussian membership function does not work and discretizes linear and non-linear functions appropriately. Thus, the proposed method is universally applicable to solve more challenges of FR viz. illumination, occlusion, expression etc. and also has application in other areas viz. medical image processing, decision making problems, hand written words recognition, speech processing, watermarking etc. Also, our method makes FR systems computationally more efficient and cost effective by using sparse concept to matrices, which makes system to consume less memory and process data faster.

Multiple kernel locality-constrained collaborative representation-based discriminant projection for face recognition

Abstract Collaborative representation-based classifier (CRC) has achieved superior classification performance in the field of face recognition. However, the performance of CRC will degrade significantly when facing non-linear structural data. To address this problem, many kernel CRC (KCRC) methods have been proposed. These methods usually use a predetermined kernel function which is difficult to be selected. In addition, how to select appropriate parameters remains a challenging problem. Hence, multiple kernel technology (MKL) is applied on CRC, which called MK-CRC. However, it only considers the representation errors while ignoring the class label information in the training process. In this paper, we propose a multiple kernel locality-constrained collaborative representation-based classifier (MKLCRC) which is the multiple kernel extension of CRC and considers the local structures of data. Based on the classification rule of MKLCRC, we propose a dimensionality reduction (DR) method called multiple kernel locality-constrained collaborative representation-based discriminant projection (MKLCR-DP). The goal of MKLCR-DP is to learn a projection matrix and a set of kernel weights to generate a low-dimensional subspace where the between-class reconstruction errors are maximized and the within-class reconstruction errors are minimized. Thus MKLCRC can achieve better performance in this low-dimensional subspace. The proposed method can be efficiently optimized with the trace ratio optimization. Experiments on AR, extended Yale B, FERET, CMU PIE and LFW face databases demonstrate that our method outperforms related state-of-the-art algorithms.

Overview of Occlusion Face Recognition Technology

Face recognition is a biometric techniques that based on the comparison and analysis of individual facial contour patterns, it can uniquely identify or verify people. In the process of carding and reviewing the development of face recognition technology, this paper introduces the problem of face recognition under the condition of occlusion which is more and more important in the field of face recognition. Through the analysis and comparison of the several occlusion face recognition algorithms, the advantages and disadvantages of these methods and their application are recognized.

Sparsifying transform learning for face image classification

Sparse signal representation showed promising results in the field of face recognition in the past few years. An algorithm based on a sparsifying transform is considered. It mainly learns a dictionary that can transform the image into sparse vectors. In the transformation domain, the images of the same class should have similar non-zero coefficients pattern that can be used for identification. The classification process of this method only requires to transform the image and make norm comparisons to determine the class of the image. The proposed method shows a comparable performance with the other known methods in the literature by means of accuracy. A novel method in sparsity-based image identification that uses analysis dictionaries is proposed, unlike the conventional sparsity-based methods. One advantage of the proposed algorithm is the low computational cost of the classification process.

Research on Face Recognition Based on CNN

With the development of deep learning, face recognition technology based on CNN (Convolutional Neural Network) has become the main method adopted in the field of face recognition. In this paper, the basic principles of CNN are studied, and the convolutional and downsampled layers of CNN are constructed by using the convolution function and downsampling function in opencv to process the pictures. At the same time, the basic principle of MLP Grasp the full connection layer and classification layer, and use Python's theano library to achieve. The construction and training of CNN model based on face recognition are studied. To simplify the CNN model, the convolution and sampling layers are combined into a single layer. Based on the already trained network, greatly improve the image recognition rate.

Comprehensive review of continuous and discrete orthogonal moments in biometrics

ABSTRACTOrthogonal moments (OM) are extensively used for image enhancement, representation and comparison. They are basically derived through mutually perpendicular polynomials which may be continuous and discrete. Primary continuous OM include Zernike, Pseudo-Zernike, Legendre and Bessel–Fourier moments and the prominent discrete OM are Krawtchouk and Tchebichef moments. These moments involve minimum information redundancy and therefore can be applied to various fields like face recognition, edge detection, palm print verification and content-based retrieval. This paper presents the comparative review of the moments in the fields of face, palm print and iris recognition. OM yield better results than non-orthogonal moments because they are robust to noise as well as rotation, scaling and transformation invariant. This paper summarizes the work done by various authors in biometrics for both continuous and discrete moments.

Sparse projections matrix binary descriptors for face recognition

Abstract In recent years, the binary feature descriptor has achieved great success in face recognition (FR) field, such as local binary pattern (LBP). It is well known that the high-dimensional feature representations can contain more discriminative information, therefore, it is natural for us to construct the high-dimensional binary feature for FR task. However, the high-dimensional representations would lead to high computational cost and overfitting. Therefore, an effective sparsity regularizer is necessary. In this paper, we introduce the sparsity constraint into the objective function of general binary codes learning framework, so that the problem of high computational cost and overfitting can be somehow solved. There are three main requirements in our objective function: First, we require that the high-dimensional binary codes have the minimized quantization loss compared with centered original data. Second, we require the projection matrices are sparse, so that the projection process would not take lots of computational resource even faced with high-dimensional original data. Third, for a mapping (hashing) function, the bit-independence and bit-balance are two excellent properties for generating discriminative binary codes. We also empirically show that the high-dimensional binary codes can obtain more discriminative ability by pooling process with an unsupervised clustering method. Therefore, a discriminative and low-cost Sparse Projection Matrix Binary Descriptors (SPMBD) is learned by the data-driven way. Extensive experimental results on four public datasets show that our SPMBD descriptor outperforms other existing face recognition algorithms and demonstrate the effectiveness and robustness of the proposed methods.

Comparison of Different Neural Network Training Algorithms with Application to Face Recognition

Research in the field of face recognition has been popular for several decades. With advances in technology, approaches to solving this problems haves changed. Main goal of this paper was to compare different training algorithms for neural networks and to apply them for face recognition as it is a n

Deep Learning for Understanding Faces: Machines May Be Just as Good, or Better, than Humans

Recent developments in deep convolutional neural networks (DCNNs) have shown impressive performance improvements on various object detection/recognition problems. This has been made possible due to the availability of large annotated data and a better understanding of the nonlinear mapping between images and class labels, as well as the affordability of powerful graphics processing units (GPUs). These developments in deep learning have also improved the capabilities of machines in understanding faces and automatically executing the tasks of face detection, pose estimation, landmark localization, and face recognition from unconstrained images and videos. In this article, we provide an overview of deep-learning methods used for face recognition. We discuss different modules involved in designing an automatic face recognition system and the role of deep learning for each of them. Some open issues regarding DCNNs for face recognition problems are then discussed. This article should prove valuable to scientists, engineers, and end users working in the fields of face recognition, security, visual surveillance, and biometrics.

Clustering and Jarque-Bera Normality Test to Face Recognition

The normality tests are widely used to estimate the difference between an empirical distribution and the normal distribution. In this paper, we propose to apply the Jarque–Bera normality test (JB-test) in the face recognition field. In order to find out the face areas, which can be approximately represented using a normal distribution, we propose to build a new descriptor based on the JB- test and Local Binary Pattern (LBP) descriptor. To predict whether a pixel belongs to the homogeneous area, Jarque–Bera Local Binary Pattern (JB-LBP) computes the confidence interval basing on the JB- test and uses it later to generate a new pixel grayscale value. The obtained results show that the homogeneous areas pixels are in same way encoded. Therefore, we can easily distinguish them from the peaks areas. Moreover, to reveal that the proposed face representation gives better performances, we combine it with the K-means clustering, the K-Nearest Neighbors (KNN) and the Multi-layers Perceptron (MLP).