Face Recognition Performance Research Articles

Force Field Feature Extraction Using Fast Algorithm for Face Recognition Performance

Face recognition is method of recognizing individuals by facial expressions. It has become essential for security and surveillance applications, including banks, organisations, workplaces, and social areas, and is needed everywhere. In face recognition, there are a variety of difficulties faced, including face shape, age, sex, lighting, and other variable factors. Another problem is that the scale of the servers for these apps is relatively limited. Education and acknowledgment, thus, are increasingly complicated. In recent years, many unchanged features have been proposed in the literature, in this paper approach the use of the fast algorithm as local descriptors, and as we shall see, it is not only fixed-size features, but also offers the advantage of being highly efficient. The proposed approach allows distinguishing the destination after converting the image to the HSV system, after which the force field features will be extracted using the fast algorithm and then classification by using the distance for three methods (Manhattan, Euclidean, and Cosine) through which a comparison is made to choose the best resolution, as it was found that the resulting accuracy of the two dataset (ORL and UFI) is 99.9%.

Extraordinary face recognition performance in laboratory and online testing

AbstractThe Cambridge Face Memory Test Long (CFMT+) is used to investigate extraordinary face recognition abilities (super‐recognizers [SR]). Whether lab and online presentation of the CFMT+ lead to different test performance has not yet been investigated. Furthermore, we wanted to investigate psychometric properties of the CFMT+ and the Glasgow face matching test – short (GFMT‐S). We report item difficulties, Cronbach's Alpha, and T norms for the CFMT+ and GFMT‐S depending on the presentation mode. We analyzed variations of CFMT+ and GFMT‐S performance by means of presentation mode, age, and gender. The results showed significant better CFMT+ performance for online presentation, women, and participants between 26 and 35 years of age. For the GFMT‐S, significantly higher test performance was shown for online participants exclusively. Overall, we discuss the modulating effects of participants' motivation for online assessments, the necessity of differential norms (e.g., for personnel decisions), and the application of T norms.

Face recognition in beginning readers: Investigating the potential relationship between reading and face recognition during the first year of school

ABSTRACT Reading acquisition has been suggested to drive the lateralization of the face processing system to the right cerebral hemisphere. To investigate whether this developmental co-dependency has a behavioural cost, at least in the short run, we tested whether learning to read reduced face recognition ability. In a longitudinal design, 82 children (5–7 years) were tested twice, at the beginning and end of their first year in school. In both sessions, visual letter recognition, word recognition, sentence reading, and immediate face recognition were tested. Reliable increases were found across all four measures, suggesting no absolute cost of literacy acquisition on face processing efficiency. In addition, we found no evidence suggesting a negative relationship between literacy acquisition and face recognition performance. Indeed, our results were most supportive of the null hypothesis suggesting independence in the development of literacy and face processing skills on the behavioural level.

Hyperspectral face recognition with a spatial information fusion for local dynamic texture patterns and collaborative representation classifier

Hyperspectral face recognition provides improved classification rates due to its abundant information in the face cubes of every subject in hyperspectral face databases. However, while offering excellent opportunities, it also brings new challenges, such as low signal-to-noise ratio, interband misalignment, and high data dimensionality. Based on these ad hoc problems, literature has already proposed some optimisation methods including dimensionality reduction, image denoising, and alignment to perform face recognition, yet lacking comprehensive evaluation. This paper proposes a novel hyperspectral face recognition algorithm that is based on spatial information fusion for feature extraction (histogram of local dynamic texture patterns) and collaborative representation classifier for classification. Meanwhile, the algorithm is applied to three popular hyperspectral face databases, Carnegie Mellon University (CMU)-hyperspectral face database (HSFD), University of Western Australia (UWA)-HSFD, and Hong Kong Polytechnic University (PolyU)-HSFD databases. Experimental results demonstrate that CMU-HSFD and UWA-HSFD databases achieve very competitive classification results. PolyU-HSFD database also achieves rather good classification rates. The best recognition results are 98.5% ± 0.95, 96.6% ± 0.98, and 94.0% ± 2.86 for CMU-HSFD, UWA-HSFD and PolyU-HSFD, respectively. It demonstrates experimentally that this algorithm can be used to recognise faces. Moreover, we compared eight existing state-of-the-art face recognition techniques with our proposed method in performing hyperspectral face recognition. In this research, we formulate hyperspectral face recognition as an image-set classification problem and evaluate the performances compared with other kinds of algorithms. Comparisons with the eight existing hyperspectral face recognition techniques on three standard datasets show that the proposed algorithm outperforms most other state-of-the-art algorithms, indicating that it is a promising approach for hyperspectral face recognition.

Do portrait artists have enhanced face processing abilities? Evidence from hidden Markov modeling of eye movements

Recent research has suggested the importance of part-based information in face recognition in addition to global, whole-face information. Nevertheless, face drawing experience was reported to enhance selective attention to the eyes but did not improve face recognition performance, leading to speculations about limited plasticity in adult face recognition. Here we examined the mechanism underlying the limited advantage of face drawing experience in face recognition through the Eye Movement analysis with Hidden Markov Models (EMHMM) approach. We found that portrait artists showed more eyes-focused eye movement patterns and outperformed novices in face matching, and participants' drawing rating was correlated with both eye movement pattern and performance. In contrast, portrait artists did not outperform novices and did not differ from novices in eye movement pattern in either the face recognition or part-whole tasks, although the eyes-focused pattern was associated with better recognition performance and longer response times in the whole condition relative to the part condition. Interestingly, in contrast to the face recognition and part-whole tasks, participants' performance in face matching was predicted by their drawing rating but not eye movement pattern. These results suggested that artists' advantage in face processing is specific to tasks similar to their drawing experience such as face matching, and may be related to their better ability in extracting identity-invariant information between two faces rather than more eyes-focused eye movement patterns.

LAMP-HQ: A Large-Scale Multi-pose High-Quality Database and Benchmark for NIR-VIS Face Recognition

Near-infrared-visible (NIR-VIS) heterogeneous face recognition matches NIR to corresponding VIS face images. However, due to the sensing gap, NIR images often lose some identity information so that the NIR-VIS recognition issue is more difficult than conventional VIS face recognition. Recently, NIR-VIS heterogeneous face recognition has attracted considerable attention in the computer vision community because of its convenience and adaptability in practical applications. Various deep learning-based methods have been proposed and substantially increased the recognition performance, but the lack of NIR-VIS training samples leads to the difficulty of the model training process. In this paper, we propose a new $$\mathbf{L} {} \mathbf{a} $$ rge-Scale $$\mathbf{M} $$ ulti- $$\mathbf{P} $$ ose $$\mathbf{H} $$ igh- $$\mathbf{Q} $$ uality NIR-VIS database ‘ $$\mathbf{LAMP}-HQ $$ ’ containing 56,788 NIR and 16,828 VIS images of 573 subjects with large diversities in pose, illumination, attribute, scene and accessory. We furnish a benchmark along with the protocol for NIR-VIS face recognition via generation on LAMP-HQ, including Pixel2-Pixel, CycleGAN, ADFL, PCFH, and PACH. Furthermore, we propose a novel exemplar-based variational spectral attention network to produce high-fidelity VIS images from NIR data. A spectral conditional attention module is introduced to reduce the domain gap between NIR and VIS data and then improve the performance of NIR-VIS heterogeneous face recognition on various databases including the LAMP-HQ.

Texture descriptors for better face recognition performance

Due to, the great electronic development, which reinforced the need to define people’s identities, different methods, and databases to identification people’s identities have emerged. In this paper, we compare the results of two texture analysis methods: Local Binary Pattern (LBP) and Local Ternary Pattern (LTP). The comparison based on comparing the extracting facial texture features of 40,401 and 10 subjects taken from ORL, UFI and Self-Created databases respectively. As well, the comparison has taken in the account using three distance measurements such as; Manhattan Distance (MD), Euclidean Distance (ED), and Cosine Distance (CD). Where the maximum accuracy of the LBP method (99.23%) is obtained with a Manhattan and ORL database as standard database, while the LTP method attained (98.76%) using the same distance and database. While, the facial database of UFI shows low quality, which is satisfied 75.98% and 73.82% recognition rates using LBP and LTP respectively with Manhattan distance. Hereby, the LBP based biometric system performs excellence recognition accuracy even with difficult face images that contain different expressions, different poses, and varied illumination like the UFI dataset.

Cropping and attention based approach for masked face recognition.

The global epidemic of COVID-19 makes people realize that wearing a mask is one of the most effective ways to protect ourselves from virus infections, which poses serious challenges for the existing face recognition system. To tackle the difficulties, a new method for masked face recognition is proposed by integrating a cropping-based approach with the Convolutional Block Attention Module (CBAM). The optimal cropping is explored for each case, while the CBAM module is adopted to focus on the regions around eyes. Two special application scenarios, using faces without mask for training to recognize masked faces, and using masked faces for training to recognize faces without mask, have also been studied. Comprehensive experiments on SMFRD, CISIA-Webface, AR and Extend Yela B datasets show that the proposed approach can significantly improve the performance of masked face recognition compared with other state-of-the-art approaches.

Regularization and attention feature distillation base on light CNN for Hyperspectral face recognition

The hyperspectral imaging, capturing discriminative information across a series of spectrum bands, leads to building a robust face recognition system. Motivated by the success of deep convolutional network and transferring learning, this paper proposed an end-to-end hyperspectral face recognition model based on a light Convolutional Neural Network (CNN) and transfer learning. To boost the performance of hyperspectral face recognition, the Max-Feature-Map (MFM) activation function and fine-tuning (structure regularization(L2SP) or attention feature distillation (AFD)) are introduced to optimize the deep network, which will learn the fine feature representation across different bands. Especially, this method incorporates regularization and AFD cooperation into the transfer learning strategy on the visible face data. By feeding back hyperspectral images to the pretrained light CNN network, we can design an end-to end model that can leverage the generalization ability for hyperspectral face images. Finally, the entire model is trained and verified on the PolyU-HSFD, CMU, and UWA hyperspectral face datasets using the associated standard evaluation protocols. Experimental results demonstrate that the improved Light CNN network can get good representations of hyperspectral face features and the joint training with a combination of L2SP and AFD exhibits better recognition performance than the state-of-the-art methods based on other deep networks.

An approach to enhance age invariant face recognition performance based on gender classification

There is a need for facial biometric based authentication system that responds quickly despite large number of registered users. The main challenge in these authentication systems is accuracy along with quick response time. The response time can be lowered by having lesser number of comparisons of the probe image with gallery images. To enhance the response time we propose gender classification as a pre-processing stage so that the validation of the user continues by taking only those facial images which are in accordance with the gender of the user. We have used Principal Component Analysis to create male and female Eigen spaces during the training phase of the classifier.To validate our classifier we have used ORL, Indian and FG-NET databases. Our proposed method gives improved recognition accuracy for the images having ageing variations.The proposed Gender classification model gives an improved accuracy of 57.44%, 59.13% and 61.13 % for the probe images taken from the FG-NET database with training images from ORL, Indian and FG-NET databases respectively as compared to PCA.Also the number of comparisons are reduced by an average of 38% by incorporating the gender classification as the pre-processing stage in the age invariant face recognition system.

Associations between self-reported and objective face recognition abilities are only evident in above- and below-average recognisers.

The 20-Item Prosopagnosia Items (PI-20) was recently introduced as a self-report measure of face recognition abilities and as an instrument to help the diagnosis of prosopagnosia. In general, studies using this questionnaire have shown that observers have moderate to strong insights into their face recognition abilities. However, it remains unknown whether these insights are equivalent for the whole range of face recognition abilities. The present study investigates this issue using the Mandarin version of the PI-20 and the Cambridge Face Memory Test Chinese (CFMT-Chinese). Our results showed a moderate negative association between the PI-20 and the CFMT-Chinese. However, this association was driven by people with low and high face recognition ability, but absent in people within the typical range of face recognition performance. The implications of these results for the study of individual differences and the diagnosis of prosopagnosia are discussed.

Robust face recognition based on multi-task convolutional neural network.

Due to the lack of prior knowledge of face images, large illumination changes, and complex backgrounds, the accuracy of face recognition is low. To address this issue, we propose a face detection and recognition algorithm based on multi-task convolutional neural network (MTCNN). In our paper, MTCNN mainly uses three cascaded networks, and adopts the idea of candidate box plus classifier to perform fast and efficient face recognition. The model is trained on a database of 50 faces we have collected, and Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index Measurement (SSIM), and receiver operating characteristic (ROC) curve are used to analyse MTCNN, Region-CNN (R-CNN) and Faster R-CNN. The average PSNR of this technique is 1.24 dB higher than that of R-CNN and 0.94 dB higher than that of Faster R-CNN. The average SSIM value of MTCNN is 10.3% higher than R-CNN and 8.7% higher than Faster R-CNN. The Area Under Curve (AUC) of MTCNN is 97.56%, the AUC of R-CNN is 91.24%, and the AUC of Faster R-CNN is 92.01%. MTCNN has the best comprehensive performance in face recognition. For the face images with defective features, MTCNN still has the best effect. This algorithm can effectively improve face recognition to a certain extent. The accuracy rate and the reduction of the false detection rate of face detection can not only be better used in key places, ensure the safety of property and security of the people, improve safety, but also better reduce the waste of human resources and improve efficiency.

Reciprocal kernel-based weighted collaborative–competitive representation for robust face recognition

The Gaussian kernel function is widely used to encode the nonlinear correlations of the face images. However, some issues greatly limit its superiority, for example, it is sensitive to the parameter setting because of its definition based on the exponential operation, on the other hand, the Gaussian kernel needs costly computational time. Besides, the hidden information such as the distance information of the samples is conducive to improving the performance of face recognition. To overcome the above problems, we propose a reciprocal kernel-based weighted collaborative–competitive representation for face recognition. Different from other methods, a new reciprocal kernel is designed to realize the nonlinear representation of the samples. Moreover, a new weight based on the reciprocal kernel is imposed on coding coefficients to disclose the hidden information of the samples in the nonlinear space. With the help of the collaborative–competitive method, the proposed method can well achieve the trade-off between collaborative and competitive representation to promote the performance of face recognition. These factors explicitly encourage the proposed method to be a better representation-type classifier. Finally, extensive experiments are conducted on five benchmark datasets, and the experimental results show that the proposed approach outperforms many state-of-the-art approaches.

Image processing effects on the deep face recognition system.

Face recognition technology has become an important quantitative examination method in the field of forensic identification of human images. However, face image quality affects the recognition performance of face recognition systems. Existing research on the effects of face image denoising and enhancement methods on the face recognition performance are typically based on facial images with manually synthesized noises rather than the noises under natural environmental corruption, and their studied face recognition techniques are limited on the traditional face recognition algorithms rather than state-of-the-art convolutional neural network based face recognition methods. In this work, face image materials from 33 real cases in forensic identification of human images were collected for quantitative analysis of the effects of face image denoising and enhancement methods on the deep face recognition performance of the MXNet system architecture based face recognition system. The results show that face image quality has a significant effect on the recognition performance of the face recognition system, and the image processing techniques can enhance the quality of face images, and then improve the recognition precision of the face recognition system. In addition, the effects of the Gaussian filtering are better than the self-snake model based image enhancement method, which indicates that the image denoising methods are more suitable for performance improvement of the deep face recognition system rather than the image enhancement techniques under the application of the practical cases.

A Study on the Performance of Unconstrained Very Low Resolution Face Recognition: Analyzing Current Trends and New Research Directions

In the past decade, research in the face recognition area has advanced tremendously, particularly in uncontrolled scenarios (face recognition in the wild). This advancement has been achieved partly due to the massive popularity and effectiveness of deep convolutional neural networks and the availability of larger unconstrained datasets. However, several face recognition challenges remain in the context of very low resolution homogeneous (same domain) and heterogeneous (different domain) face recognition. In this survey, we study the seminal and novel methods to tackle the very low resolution face recognition problem and provide an in-depth analysis of their design, effectiveness, and efficiency for a real-time surveillance application. Furthermore, we analyze the advantage of employing deep learning convolutional neural networks, while presenting future research directions for effective deep learning network design in this context.

Weighted Feature Histogram of Multi-Scale Local Patch Using Multi-Bit Binary Descriptor for 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.

Face Hallucination With Finishing Touches.

Obtaining a high-quality frontal face image from a low-resolution (LR) non-frontal face image is primarily important for many facial analysis applications. However, mainstreams either focus on super-resolving near-frontal LR faces or frontalizing non-frontal high-resolution (HR) faces. It is desirable to perform both tasks seamlessly for daily-life unconstrained face images. In this paper, we present a novel Vivid Face Hallucination Generative Adversarial Network (VividGAN) for simultaneously super-resolving and frontalizing tiny non-frontal face images. VividGAN consists of coarse-level and fine-level Face Hallucination Networks (FHnet) and two discriminators, i.e., Coarse-D and Fine-D. The coarse-level FHnet generates a frontal coarse HR face and then the fine-level FHnet makes use of the facial component appearance prior, i.e., fine-grained facial components, to attain a frontal HR face image with authentic details. In the fine-level FHnet, we also design a facial component-aware module that adopts the facial geometry guidance as clues to accurately align and merge the frontal coarse HR face and prior information. Meanwhile, two-level discriminators are designed to capture both the global outline of a face image as well as detailed facial characteristics. The Coarse-D enforces the coarsely hallucinated faces to be upright and complete while the Fine-D focuses on the fine hallucinated ones for sharper details. Extensive experiments demonstrate that our VividGAN achieves photo-realistic frontal HR faces, reaching superior performance in downstream tasks, i.e., face recognition and expression classification, compared with other state-of-the-art methods.

MTCNN and FACENET Based Access Control System for Face Detection and Recognition

Face detection and recognition is one of the research hotspots in the field of computer vision, which is widely used in video surveillance and identity matching. The traditional algorithms of face detection include AdaBoost, Haar-like, DPM, etc. These algorithms use face geometric features and template matching for face detection, which is difficult to consider both detection speed and accuracy. In order to solve this problem, this paper proposes an improved FaceNet network. The multi-task cascaded convolutional neural networks (MTCNN) is used to achieve rapid face detection and face alignment, and then the FaceNet with improved loss function is used to realize face verification and recognition with high accuracy. We compare the face detection and recognition performance of our network framework with the traditional algorithms and some deep learning algorithms. The experimental results verify that the improved FaceNet can meet the requirements of real-time recognition, and the recognition accuracy reaches 99.85%, which meets the actual demand. It can be effectively applied to face detection and recognition in the Access Control System.

Application of Face Recognition Method Under Deep Learning Algorithm in Embedded Systems

The Convolutional Neural Network (CNN) based on deep learning is introduced to propose two deep face detection algorithms and design an embedded face recognition system, in an effort to apply the deep learning algorithm to face detection and explore the embedded face recognition system. First, an optimized Multi-task Cascaded Convolutional Network (MTCNN) algorithm is proposed for the simulation transformation and crop preprocessing of the face image, denoted as OMTCNN. Second, a lightweight face recognition algorithm based on CNN is proposed to reduce the computational complexity of face recognition in the embedded system, denoted as LCNN. Finally, OMTCNN and LCNN are combined to construct the multi-core embedded face recognition system. Results demonstrate that OMTCNN shows good performance in determining face identity, and its training accuracy can reach 95.78%, significantly better than the unimproved MTCNN algorithm. On the Labeled Faces in the Wild (LFW) dataset, LCNN provides a correct rate of 98.13%, and the reduction in the complexity of the model itself increases the computational speed by as much as 6.4 times. The test results suggest that the designed face recognition system has good applicability on the embedded platform. The increase in the accuracy of the face recognition module and the introduction of the calculation acceleration module have significantly improved the face detection and recognition performance of the embedded system. The embedded face recognition system based on deep learning has practical application value.

Filter selection for image processing before the landmark detection stage for micro-expression analysis

The automated estimation of the psycho-emotional state of the human and their emotional reactions to the different influences using the video image analysis is an urgent task in different fields, such as: safeguarding in manufacturing, aviation, transportation, prevention of the crimes and terroristic threats, marketing researches etc. A promising direction is the facial micro-expression analysis. The facial micro-expressions are not under conscious control and reflect the objective emotional reaction. One of the key stages of the procedure of the automatic emotion estimation by the facial micro-expressions is the correct facial landmark detection. It is a complex task because of the presence of the different noise in the consecutive frames. Purpose – the investigation of the ways of increasing the performance of the facial micro-expression analysis pipeline by using preliminary video image processing procedures. It is shown that, as the preliminary stage of the micro-expression analysis pipeline, it is reasonable to perform the blurring of the original images to obtain the more stable results. The determined filtering parameters provide the MediaPipe framework a performance increase for the micro-expression analysis problems. It is shown that the video image blurring by the Gaussian filter with a size of 15×15 pixels allows to reduce the noise influence and to decrease the incorrect shifts of the facial landmarks from frame to frame induced by this noise. The proposed procedure of preliminary video image processing can be used for increasing the facial micro-expression recognition performance in emotion recognition systems based on the video sequence analysis.