Human sensing using the mutual subspace method with multi-view images

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.

In recent days, there has been increasing need for recognition of unconstrained face images, such as those collected from the web or captured by mobile devices and video surveillance cameras. In such real world scenarios, human faces could be easily occluded by other objects that make the face recognition task as a complex one. Satisfactory performance has been achieved earlier but often only in the controlled environments. But it is very tedious to obtain holistic face images for unconstrained face recognition. Thus, in order to avoid the degradation of face images and the huge variations due to illumination, pose, occlusion and expression, a new Robust Face Recognition approach is proposed. In this approach, the partial face recognition using Scale Invariant Feature Transform (SIFT) technique is combined with Multi-directional Multi-level Dual Cross Patterns (DCP) technique that makes the recognition task as a robust one when compared to other face recognition approaches. Then, the Robust Point Set Matching (RPSM) is used to match the corresponding stable keypoints from both the gallery image and probe face image. Finally, PNN and K-NN classification are used to classify the face images even with the presence of occlusion, random partial crop, illumination, pose and exaggerated facial expression. The proposed robust face recognition system is evaluated based on the performance parameters such as sensitivity, specificity, accuracy, precision and recall.

Face recognition has been a major research theme over the last two decades. There are several problems to be solved to improve the performance of face recognition. Such major problems involve appearance variation due to pose, illumination, expression, and aging. In particular, aging includes internal and external factors that cause facial appearance variation and, consequently, it is the most difficult problem to handle. In this paper, we propose a face recognition method that is robust against facial appearance variation due to aging. The proposed method employs segmentation verification of frontal face images that consists of the following three steps. (1) Face image segmentation generates three regional subimages from the input face image. (2) A matching score is calculated using gradient features from a pair consisting of the input image and a registered image for each of the three generated subimages and original (whole face) image. We obtain four matching scores. (3) The verifying classifier evaluates the matching score vector formed of the matching scores calculated for each of the four images and predicts the a posteriori probability that two matching images belong to the same person. The results of an experimental evaluation with the FGNET and MORPH face aging datasets clarify the effectiveness of the proposed method for age invariant face recognition.

Facial albedo images are believed to be invariant to external factors of pose, illumination and expression that can greatly affect the appearance of face images and thus face recognition accuracy as well. Unlike most existing face recognition methods that address the impact of one or two of these external factors, we propose an end-to-end network, which consists of De-Light Network (DL-Net) and Normalization Network (N-Net), to generate normalized albedo images with neutral expression and frontal pose for input face images. DL-Net aims to eliminate the effects of illumination and reconstruct a posed albedo image that has the same pose and expression as the input image. N-Net attempts to generate a pose and expression normalized albedo image and extract identity features under the supervision of the normalized albedo images. Our experiments on the Multi-PIE database show that the extracted identity features can effectively assist conventional face recognition methods to improve face recognition accuracy under varying poses, illuminations and expressions.

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 recognition has attracted great interest due to its importance in many real-world applications. In this paper, we present a novel low-rank sparse representation-based classification (LRSRC) method for robust face recognition. Given a set of test samples, LRSRC seeks the lowest-rank and sparsest representation matrix over all training samples. Since low-rank model can reveal the subspace structures of data while sparsity helps to recognize the data class, the obtained test sample representations are both representative and discriminative. Using the representation vector of a test sample, LRSRC classifies the test sample into the class which generates minimal reconstruction error. Experimental results on several face image databases show the effectiveness and robustness of LRSRC in face image recognition.

Robust face recognition using 2D and 3D data: Pose and illumination compensation

When creating a multi-view image for multi-view 3D display with one camera, the camera has to be moved from one viewpoint to another viewpoint. However, this method takes long time and can not get images of a moving object. In this paper, we proposed the method for capturing a multi-view image by one step. In order to capture a multi-view image, the lenticular lens is used in our proposed system. The captured multi-view image becomes reverse by using the lenticular lens. Before calculating the best observation distance, a reversal processing is performed. To display a multi-view 3D image by the multi-view image, the same lenticular lens is used. As an experiment result, we got the multi-view image by our proposal system. When we laid the multi-view image under the lenticular lens, a multi-view 3D image with deep feeling was confirmed.

Depth information has been proven useful for face recognition. However, existing depth-image-based face recognition methods still suffer from noisy depth values and varying poses and expressions. In this paper, we propose a novel method for normalizing facial depth images to frontal pose and neutral expression and extracting robust features from the normalized depth images. The method is implemented via two deep convolutional neural networks (DCNN), normalization network (\(Net_{N}\)) and feature extraction network (\(Net_{F}\)). Given a facial depth image, \(Net_{N}\) first converts it to an HHA image, from which the 3D face is reconstructed via a DCNN. \(Net_{N}\) then generates a pose-and-expression normalized (PEN) depth image from the reconstructed 3D face. The PEN depth image is finally passed to \(Net_{F}\), which extracts a robust feature representation via another DCNN for face recognition. Our preliminary evaluation results demonstrate the superiority of the proposed method in recognizing faces of arbitrary poses and expressions with depth images.

In this chapter, we describe a new robust face recognition system base on a multi-views face database that derives some 3-D information from a set of face images. We attempt to build an approximately 3-D system for improving the performance of face recognition. Our objective is to provide a basic 3-D system for improving the performance of face recognition. The main goal of this vision system is 1) to minimize the hardware resources, 2) to obtain high success rates of identity verification, and 3) to cope with real-time constraints. Using the multi-views database, we address the problem of face recognition by evaluating the two methods PCA and ICA and comparing their relative performance. We explore the issues of subspace selection, algorithm comparison, and multi-views face recognition performance. In order to make full use of the multi-views property, we also propose a strategy of majority voting among the five views, which can improve the recognition rate. Experimental results show that ICA is a promising method among the many possible face recognition methods, and that the ICA algorithm with majority-voting is currently the best choice for our purposes.

A novel face recognition method is proposed, in which face images are represented by a set of local labeled graphs, each containing information about the appearance and geometry of a 3-tuple of face feature points, extracted using Local Feature Analysis (LFA) technique. Our method automatically learns a model set and builds a graph space for each individual. A two-stage method for optimal matching between the graphs extracted from a probe image and the trained model graphs is proposed. The recognition of each probe face image is performed by assigning it to the trained individual with the maximum number of references. Our approach achieves perfect result on the ORL face set and an accuracy rate of 98.4% on the FERET face set, which shows the superiority of our method over all considered state-of-the-art methods. I

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.

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

We describe a new method for recognizing humans by their face, which is robust to the variations of facial imaging conditions, with high accuracy. The human face recognition system consists of three components: i) a new face descriptor based on edge component histogram and its variance between pixels, ii) Gab or-edge components histogram for facial image representation, combining the Gab or wavelet and the proposed edge components histogram, iii) a sparse representation classifier for the face recognition. The effective and robust face recognition with high accuracy is achieved by the Gab or-edge components histogram and the sparse representation classifier. In experiments, higher face recognition performances, which are 99.45% on ETRI database and 99.41% on XM2VTS database, have been achieved.