Enhancing face recognition in native low-resolution images using deep learning and bicubic interpolati

Because face recognition is greatly affected by external environmental factors and the partial lack of face information challenges the robustness of face recognition algorithm, while the existing methods have poor robustness and low accuracy in face image recognition, this paper proposes a face image digital processing and recognition based on data dimensionality reduction algorithm. Based on the analysis of the existing data dimensionality reduction and face recognition methods, according to the face image input, feature composition, and external environmental factors, the face recognition and processing technology flow is given, and the face feature extraction method is proposed based on nonparametric subspace analysis (NSA). Finally, different methods are used to carry out comparative experiments in different face databases. The results show that the method proposed in this paper has a higher correct recognition rate than the existing methods and has an obvious effect on the XM2VTS face database. This method not only improves the shortcomings of existing methods in dealing with complex face images but also provides a certain reference for face image feature extraction and recognition in complex environment.

Face recognition in low-quality images using adaptive sparse representations

Face recognition is one of the most common authentication techniques widely used due to its easy access. In many face recognition applications, captured images are often of low resolution. Face recognition methods perform poorly on low resolution images because they are trained on high resolution face images. Although existing face hallucination methods may generate visually pleasing images, they cannot improve the performance of face recognition methods at low resolution as the structure of the face image and high-frequency details are not sufficiently preserved. Recent advances in deep learning have been used in this paper to propose a new face super-resolution approach to empower face recognition methods. In this paper, a Generative Adversarial Network is used to empower face recognition in low-resolution images. This network considers image edges and reconstructs high-frequency details to preserve the face structure. The proposed technique to generate super-resolved features is usable in any face recognition method. We have used some state-of-the-art face recognition methods to evaluate the proposed method. The results showed a significant impact of the proposed method on the accuracy of face recognition of low resolution images.

Nowadays, face recognition has gained more consideration in the area of image processing and computer vision. The existing face recognition systems provide better performance using the frontal images with high resolution. The major issue in face recognition is the Low-Resolution face images. To alleviate this issue, this paper proposes the face recognition system by integrating the Gabor filter + wavelet + texture (GWTM) operator and the Crow search algorithm to increase the classification performance, while deploying the LR images. Initially, the input image is given to the preprocessing, and the low-resolution image is generated. Then, this low-resolution image is applied to the kernel regression model to produce the image with high-resolution. Then, both the low-resolution and the high-resolution images are applied to the GWTM operator for extracting the features. The result of the GWTM is provided to the Crow search algorithm for producing the intermediate images. Finally, the intermediate images are given to the spherical SVM classifier for optimal recognition. The performance of the proposed method is analyzed with the existing methods using three evaluation metrics, such as accuracy, FAR, and FRR. From the experimental results, it can be show that the proposed method attains the higher accuracy of 0.9500, minimum FAR and FRR of 0.0500.

Existing face recognition techniques are very successful in recognizing high-resolution facial images. However, their performance is not sufficient on low-resolution facial images. In this thesis we focus on dealing with a typical forensic scenario, where the gallery images are the high-resolution mug-shots in the police database and the probe images are the low-resolution surveillance quality facial images. We proposed a novel method, mixed-resolution biometric comparison, which allows direct low-resolution to high-resolution comparison. The method is based on the likelihood ratio framework where in the derivation of the expression for the likelihood ratio, the combined statistics of the low- and high-resolution images is taken into account. Our experiments on surveillance quality images demonstrate that this method significantly outperforms the state-of-the-art. In literature on low-resolution face recognition, what in some papers is considered as low-resolution, is still considered as high-resolution in other papers. To harmonize the terminology in low-resolution face recognition, we propose a resolution scale. We define the range of low-resolution and further divide it into Upper Low Resolution, Moderately Low Resolution and Very Low Resolution. Because the lack of low-resolution images, most of the existing low-resolution face recognition methods are trained and tested using down-sampled images. In this thesis, we test various face recognition methods and demonstrate that down-sampled images are not fully representative of realistic low-resolution images. We further demonstrate that, inaccurate alignment is the major problem that causes the poor recognition performance on real low-resolution images. In addition, we propose to use matching-score based registration to achieve better alignment and hence better face recognition performance. In conclusion, we propose solutions to compare low-resolution probes with high-resolution galleries which significantly outperform the state-of-the-art on surveillance quality facial images. We emphasise that realistic low-resolution material should be used for training and testing. We focus attention on developing face recognition methods that can actually be useful for real-life applications. We bring an important step forward of low-resolution face recognition for forensic search.

In face recognition systems, highly robust facial feature representation and good classification algorithm performance can affect the effect of face recognition under unrestricted conditions. To explore the anti‐interference performance of convolutional neural network (CNN) reconstructed by deep learning (DL) framework in face image feature extraction (FE) and recognition, in the paper, first, the inception structure in the GoogleNet network and the residual error in the ResNet network structure are combined to construct a new deep reconstruction network algorithm, with the random gradient descent (SGD) and triplet loss functions as the model optimizer and classifier, respectively, and it is applied to the face recognition in Labeled Faces in the Wild (LFW) face database. Then, the portrait pyramid segmentation and local feature point segmentation are applied to extract the features of face images, and the matching of face feature points is achieved using Euclidean distance and joint Bayesian method. Finally, Matlab software is used to simulate the algorithm proposed in this paper and compare it with other algorithms. The results show that the proposed algorithm has the best face recognition effect when the learning rate is 0.0004, the attenuation coefficient is 0.0001, the training method is SGD, and dropout is 0.1 (accuracy: 99.03%, loss: 0.0047, training time: 352 s, and overfitting rate: 1.006), and the algorithm proposed in this paper has the largest mean average precision compared to other CNN algorithms. The correct rate of face feature matching of the algorithm proposed in this paper is 84.72%, which is higher than LetNet‐5, VGG‐16, and VGG‐19 algorithms, the correct rates of which are 6.94%, 2.5%, and 1.11%, respectively, but lower than GoogleNet, AlexNet, and ResNet algorithms. At the same time, the algorithm proposed in this paper has a faster matching time (206.44 s) and a higher correct matching rate (88.75%) than the joint Bayesian method, indicating that the deep reconstruction network algorithm proposed in this paper can be used in face image recognition, FE, and matching, and it has strong anti‐interference.

Due to large distances between surveillance cameras and subjects, the captured images usually have low resolution in addition to uncontrolled poses and illumination conditions that adversely affect the performance of face recognition algorithms. In this paper, we present a low-resolution face recognition technique based on Discriminant Correlation Analysis (DCA). DCA analyzes the correlation of the features in high-resolution and low-resolution images and aims to find projections that maximize the pair-wise correlations between the two feature sets and at the same time, separate the classes within each set. This makes it possible to project the features extracted from high-resolution and low-resolution images into a common space, in which we can apply matching. The proposed method is computationally efficient and can be applied to challenging real-time applications such as recognition of several faces appearing in a crowded frame of a surveillance video. Extensive experiments performed on low-resolution surveillance images from the SCface database as well as FRGC database demonstrated the efficacy of our proposed approach in the recognition of low-resolution face images, which outperformed other state-of-the-art techniques.

Two-Dimensional Barcode Image Super-Resolution Reconstruction Via Sparse Representation

The resolution level of face images is one of the key factors affecting the performance of face recognition algorithms. Face recognition under low resolution conditions has always been a challenging research topic in related fields. Using super-resolution restoration technology to improve the spatial resolution of the face to be recognized and reconstruct its high-resolution information is an effective way to improve the performance of the algorithm. However, the traditional image super-resolution restoration algorithm generally has problems such as high computational complexity and difficulty in training, which restricts its application in the actual face recognition system. Therefore, this paper proposes a l ow-resolution face image super-resolution restoration algorithm based on simplified VGG network. Firstly, based on the degradation process of low-resolution face images, a set of face image samples corresponding to high and low resolution based on prior knowledge is constructed, and a streamlined 6-layer VGG network is designed to learn between high and low resolution images. The mapping relationship is finally achieved by deconvolution amplification to achieve the super-resolution restoration process of the image. The common LFW and ORL data sets are used to test and analyze the super-resolution restoration effect of the algorithm and its impact on the face recognition algorithm. The experimental results show that the proposed algorithm is superior to the classical SRCNN algorithm in super-resolution performance. When applied to the face recognition algorithm based on Lenet-5, its recognition performance is significantly improved.

Degradation model and attention guided distillation approach for low resolution face recognition

The characteristics of surveillance video generally include low-resolution images and blurred images. Decreases in image resolution lead to loss of high frequency facial components, which is expected to adversely affect recognition rates. Super resolution (SR) is a technique used to generate a higher resolution image from a given low-resolution, degraded image. Dictionary based super resolution pre-processing techniques have been developed to overcome the problem of low-resolution images in face recognition. However, super resolution reconstruction process, being ill-posed, and results in visual artifacts that can be visually distracting to humans and/or affect machine feature extraction and face recognition algorithms. In this paper, we investigate the impact of two existing super-resolution methods to reconstruct a high resolution from single/ multiple low-resolution images on face recognition. We propose an alternative scheme that is based on dictionaries in high frequency wavelet subbands. The performance of the proposed method will be evaluated on databases of high and low-resolution images captured under different illumination conditions and at different distances. We shall demonstrate that the proposed approach at level 3 DWT decomposition has superior performance in comparison to the other super resolution methods.

Face recognition has attracted enormous interest from researchers due to its widescale adaptation. However, most of the work in the literature is based on face recognition in controlled environments i.e., high-resolution face images with slight variation in pose, illumination and expression. CNN is used as backbone architecture in the face recognition models. Low-resolution face images having large variations in pose, illumination and expressions make a face recognition problem more challenging. It is difficult to extract discriminative features from low-resolution images. That's why the performance of face recognition models trained on high-resolution images deteriorate on low-resolution images. In this work, quality of low-resolution images is enhanced through multiple super-resolution GANs in order to improve the identification accuracy. Experiments are performed on SCface dataset and the improvement in the identification accuracy shows the effectiveness of using enhanced images generated through super-resolution GANs.

Face images captured by surveillance cameras usually have poor quality, particularly low resolution (LR), which affects the performance of face recognition seriously. In this paper, we develop a novel approach to address the problem of matching a LR face image against a gallery of relatively high resolution (HR) face images. Existing methods deal with such cross-resolution face recognition problem either by importing the information of HR images to help synthesize HR images from LR images or by applying the discrimination of HR images to help search for a unified feature space. Instead, we treat the discrimination information of HR and LR face images equally to boost the performance. The proposed approach learns resolution invariant features aiming to: (1) classify the identity of both LR and HR face images accurately, and (2) preserve the discriminative information among subjects across different resolutions. We conduct experiments on databases of uncontrolled scenarios, i.e., SCface and COX, and results show that the proposed approach significantly outperforms state-of-the-art methods.

Face images of non-frontal views under poor illumination resolution reduce dramatically face recognition accuracy. This is evident most compellingly by the very low recognition rate of all existing face recognition systems when applied to live CCTV camera input. In this paper, we present a Bayesian framework to perform multimodal (such as variations in viewpoint and illumination) face image super-resolution for recognition in tensor space. Given a single modal low-resolution face image, we benefit from the multiple factor interactions of training sensor and super-resolve its high-resolution reconstructions across different modalities for face recognition. Instead of performing pixel-domain super-resolution and recognition independently as two separate sequential processes, we integrate the tasks of super-resolution and recognition by directly computing a maximum likelihood identity parameter vector in high-resolution tensor space for recognition. We show results from multi-modal super-resolution and face recognition experiments across different imaging modalities, using low-resolution images as testing inputs and demonstrate improved recognition rates over standard tensorface and eigenface representations

There are many factors affecting visual face recognition, such as low resolution images, aging, illumination and pose variance, etc. One of the most important problem is low resolution face images which can result in bad performance on face recognition. The modern face hallucination models demonstrate reasonable performance to reconstruct high-resolution images from its corresponding low resolution images. However, they do not consider identity level information during hallucination which directly affects results of the recognition of low resolution faces. To address this issue, we propose a Face Hallucination Generative Adversarial Network (FH-GAN) which improves the quality of low resolution face images and accurately recognize those low quality images. Concretely, we make the following contributions: (1) we propose FH-GAN network, an end-to-end system, that improves both face hallucination and face recognition simultaneously. The novelty of this proposed network depends on incorporating identity information in a GAN-based face hallucination algorithm via combining a face recognition network for identity preserving. (2) We also propose a new face hallucination network, namely Dense Sparse Network (DSNet), which improves upon the state-of-art in face hallucination. (3) We demonstrate benefits of training the face recognition and GAN-based DSNet jointly by reporting good result on face hallucination and recognition.