scholarly journals A Novel Face Super-Resolution Method Based on Parallel Imaging and OpenVINO

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Zhijie Huang ◽  
Wenbo Zheng ◽  
Lan Yan ◽  
Chao Gou
Keyword(s):  
Parallel Imaging ◽  
Super Resolution ◽  
Representation Learning ◽  
Face Image ◽  
Face Images ◽  
Deep Model ◽  
Training Samples ◽  
Speed Up ◽  
Imaging Theory ◽  
Imaging Methodology

Face image super-resolution refers to recovering a high-resolution face image from a low-resolution one. In recent years, due to the breakthrough progress of deep representation learning for super-resolution, the study of face super-resolution has become one of the hot topics in the field of super-resolution. However, the performance of these deep learning-based approaches highly relies on the scale of training samples and is limited in efficiency in real-time applications. To address these issues, in this work, we introduce a novel method based on the parallel imaging theory and OpenVINO. In particular, inspired by the methodology of learning-by-synthesis in parallel imaging, we propose to learn from the combination of virtual and real face images. In addition, we introduce a center loss function borrowed from the deep model to enhance the robustness of our model and propose to apply OpenVINO to speed up the inference. To the best of our knowledge, it is the first time to tackle the problem of face super-resolution based on parallel imaging methodology and OpenVINO. Extensive experimental results and comparisons on the publicly available LFW, WebCaricature, and FERET datasets demonstrate the effectiveness and efficiency of the proposed method.

Low-resolution and open-set face recognition via recursive label propagation based on statistical classification

2019 ◽  
Vol 17 (02) ◽  
pp. 1940002 ◽  
Author(s):  
Shan Xue ◽  
Hong Zhu
Keyword(s):  
Face Recognition ◽  
Super Resolution ◽  
Recall Rate ◽  
Face Image ◽  
Label Propagation ◽  
Statistical Classification ◽  
Low Resolution ◽  
Face Images ◽  
Open Set ◽  
Discriminative Feature

In video surveillance, the captured face images are usually suffered from low-resolution (LR), besides, not all the probe images have mates in the gallery under the premise that only a single frontal high-resolution (HR) face image per subject. To address this problem, a novel face recognition framework called recursive label propagation based on statistical classification (ReLPBSC) has been proposed in this paper. Firstly, we employ VGG to extract robust discriminative feature vectors to represent each face. Then we select the corresponding LR face in the probe for each HR gallery face by similarity. Based on the picked HR–LR pairs, ReLPBSC is implemented for recognition. The main contributions of the proposed approach are as follows: (i) Inspired by substantial achievements of deep learning methods, VGG is adopted to achieve discriminative representation for LR faces to avoid the super-resolution steps; (ii) the accepted and rejected threshold parameters, which are not fixed in face recognition, can be achieved with ReLPBSC adaptively; (iii) the unreliable subjects never enrolled in the gallery can be rejected automatically with designed methods. Experimental results in [Formula: see text] pixels resolution show that the proposed method can achieve 86.64% recall rate while keeping 100% precision.

The face image super-resolution algorithm based on combined representation learning

2020 ◽  
Author(s):  
Yuantao Chen ◽  
Volachith Phonevilay ◽  
Jiajun Tao ◽  
Xi Chen ◽  
Runlong Xia ◽  
...  
Keyword(s):  
Super Resolution ◽  
Representation Learning ◽  
Face Image ◽  
The Face ◽  
Image Super Resolution ◽  
Resolution Algorithm

scholarly journals Style-Based Unsupervised Learning for Real-World Face Image Super-Resolution

2020 ◽  
Author(s):  
Ahmed Cheikh Sidiya ◽  
Xin Li
Keyword(s):  
Unsupervised Learning ◽  
Real World ◽  
Super Resolution ◽  
Image Synthesis ◽  
Face Image ◽  
Quality Improvements ◽  
Training Strategy ◽  
Face Images ◽  
Image Super Resolution ◽  
Single Image Super Resolution

Face image synthesis has advanced rapidly in recent years. However, similar success has not been witnessed in related areas such as face single image super-resolution (SISR). The performance of SISR on real-world low-quality face images remains unsatisfactory. In this paper, we demonstrate how to advance the state-of-the-art in face SISR by leveraging style-based generator in unsupervised settings. For real-world low-resolution (LR) face images, we propose a novel unsupervised learning approach by combining style-based generator with relativistic discriminator. With a carefully designed training strategy, we demonstrate our converges faster and better suppresses artifacts than Bulat’s approach. When trained on an ensemble of high-quality datasets (CelebA, AFLW, LS3D-W, and VGGFace2), we report significant visual quality improvements over other competing methods especially for real-world low-quality face images such as those in Widerface. Additionally, we have verified that both our unsupervised approaches are capable of improving the matching performance of widely used face recognition systems such as OpenFace.

scholarly journals Facial Attribute Capsules for Noise Face Super Resolution

2020 ◽  
Vol 34 (07) ◽  
pp. 12476-12483 ◽  
Author(s):  
Jingwei Xin ◽  
Nannan Wang ◽  
Xinrui Jiang ◽  
Jie Li ◽  
Xinbo Gao ◽  
...  
Keyword(s):  
Learning Strategy ◽  
Semantic Representation ◽  
Super Resolution ◽  
Semantic Space ◽  
Input Image ◽  
Face Image ◽  
Fine Grained ◽  
Face Images ◽  
Facial Information ◽  
The Face

Existing face super-resolution (SR) methods mainly assume the input image to be noise-free. Their performance degrades drastically when applied to real-world scenarios where the input image is always contaminated by noise. In this paper, we propose a Facial Attribute Capsules Network (FACN) to deal with the problem of high-scale super-resolution of noisy face image. Capsule is a group of neurons whose activity vector models different properties of the same entity. Inspired by the concept of capsule, we propose an integrated representation model of facial information, which named Facial Attribute Capsule (FAC). In the SR processing, we first generated a group of FACs from the input LR face, and then reconstructed the HR face from this group of FACs. Aiming to effectively improve the robustness of FAC to noise, we generate FAC in semantic, probabilistic and facial attributes manners by means of integrated learning strategy. Each FAC can be divided into two sub-capsules: Semantic Capsule (SC) and Probabilistic Capsule (PC). Them describe an explicit facial attribute in detail from two aspects of semantic representation and probability distribution. The group of FACs model an image as a combination of facial attribute information in the semantic space and probabilistic space by an attribute-disentangling way. The diverse FACs could better combine the face prior information to generate the face images with fine-grained semantic attributes. Extensive benchmark experiments show that our method achieves superior hallucination results and outperforms state-of-the-art for very low resolution (LR) noise face image super resolution.

Improving Flexible Manifold Embedding Method for Better Recognition of Face Images

2016 ◽  
Vol 13 (10) ◽  
pp. 7696-7700
Author(s):  
Xuansheng Wang ◽  
Zheqi Lin ◽  
Zhen Chen ◽  
Zhongming Teng
Keyword(s):  
Face Recognition ◽  
Linear Regression ◽  
Regression Function ◽  
Face Image ◽  
Mirror Image ◽  
Face Images ◽  
Manifold Embedding ◽  
Training Samples ◽  
Label Information ◽  
The Face

Flexible Manifold Embedding (FME) is a semi-supervised manifold learning framework with good applicability. FME can effectively exploit label information from labeled data as well as a manifold structure from both labeled and unlabeled data to reduce the dimension of data. FME employs a simple but effective linear regression function to map new data points and it aims to find optimal prediction labels F for all training samples X, the linear regression h(X) and the regression residue F0 = F− h(X). In this paper, we proposed a novel idea to improve the accuracy of FME. We produce the mirror image of the face and then integrate the original face image and its mirror image to extend training samples X. The mirror image shares the same class label with the original face image, so to simultaneously use the mirror image and original face image can partially eliminate the side-effect on face recognition of the variation of poses and illuminations of original face images of the same person. The proposed method combines the advantages of the FME and extended training samples for face recognition. Moreover, the mirror image used in the proposed method can also enhance the robustness of the method. Experiments carried out on public face databases show that the proposed method can obtain notable accuracy improvement.

scholarly journals Generating Images of Face Poses for Pose Varying Face Recognition

2020 ◽  
Vol 9 (2) ◽  
pp. 351-356
Keyword(s):  
Computer Vision ◽  
Deep Learning ◽  
Face Recognition ◽  
Representation Learning ◽  
Image Synthesis ◽  
Face Image ◽  
Learning Systems ◽  
Face Expression ◽  
Face Images ◽  
The Face

Deep learning has attracted several researchers in the field of computer vision due to its ability to perform face and object recognition tasks with high accuracy than the traditional shallow learning systems. The convolutional layers present in the deep learning systems help to successfully capture the distinctive features of the face. For biometric authentication, face recognition (FR) has been preferred due to its passive nature. Processing face images are accompanied by a series of complexities, like variation of pose, light, face expression, and make up. Although all aspects are important, the one that impacts the most face-related computer vision applications is pose. In face recognition, it has been long desired to have a method capable of bringing faces to the same pose, usually a frontal view, in order to ease recognition. Synthesizing different views of a face is still a great challenge, mostly because in nonfrontal face images there are loss of information when one side of the face occludes the other. Most solutions for FR fail to perform well in cases involving extreme pose variations as in such scenarios, the convolutional layers of the deep models are unable to find discriminative parts of the face for extracting information. Most of the architectures proposed earlier deal with the scenarios where the face images used for training as well as testing the deep learning models are frontal and nearfrontal. On the contrary, here a limited number of face images at different poses is used to train the model, where a number of separate generator models learn to map a single face image at any arbitrary pose to specific poses and the discriminator performs the task of face recognition along with discriminating a synthetic face from a realworld sample. To this end, this paper proposes a representation learning by rotating the face. Here an encoderdecoder structure of the generator enables to learn a representation that is both generative and discriminative, which can be used for face image synthesis and pose-invariant face recognition. This representation is explicitly disentangled from other face variations such as pose, through the pose code provided to the decoder and pose estimation in the discriminator.

scholarly journals Enhanced use of gaze cue in a face-following task after brief trial experience in individuals with autism spectrum disorder

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Takao Fukui ◽  
Mrinmoy Chakrabarty ◽  
Misako Sano ◽  
Ari Tanaka ◽  
Mayuko Suzuki ◽  
...  
Keyword(s):  
Autism Spectrum ◽  
Face Image ◽  
Fixation Time ◽  
Gaze Shift ◽  
The Gaze ◽  
Face Images ◽  
Trial Experience ◽  
Short Period ◽  
The Face ◽  
Gaze Cues

AbstractEye movements toward sequentially presented face images with or without gaze cues were recorded to investigate whether those with ASD, in comparison to their typically developing (TD) peers, could prospectively perform the task according to gaze cues. Line-drawn face images were sequentially presented for one second each on a laptop PC display, and the face images shifted from side-to-side and up-and-down. In the gaze cue condition, the gaze of the face image was directed to the position where the next face would be presented. Although the participants with ASD looked less at the eye area of the face image than their TD peers, they could perform comparable smooth gaze shift to the gaze cue of the face image in the gaze cue condition. This appropriate gaze shift in the ASD group was more evident in the second half of trials in than in the first half, as revealed by the mean proportion of fixation time in the eye area to valid gaze data in the early phase (during face image presentation) and the time to first fixation on the eye area. These results suggest that individuals with ASD may benefit from the short-period trial experiment by enhancing the usage of gaze cue.

scholarly journals A Lightweight Dense Connected Approach with Attention on Single Image Super-Resolution

Electronics ◽  
2021 ◽  
Vol 10 (11) ◽  
pp. 1234
Author(s):  
Lei Zha ◽  
Yu Yang ◽  
Zicheng Lai ◽  
Ziwei Zhang ◽  
Juan Wen
Keyword(s):  
Receptive Fields ◽  
Super Resolution ◽  
Feature Representation ◽  
Single Image ◽  
Deep Model ◽  
Benchmark Datasets ◽  
Rich Information ◽  
Image Super Resolution ◽  
Model Training ◽  
Single Image Super Resolution

In recent years, neural networks for single image super-resolution (SISR) have applied more profound and deeper network structures to extract extra image details, which brings difficulties in model training. To deal with deep model training problems, researchers utilize dense skip connections to promote the model’s feature representation ability by reusing deep features of different receptive fields. Benefiting from the dense connection block, SRDensenet has achieved excellent performance in SISR. Despite the fact that the dense connected structure can provide rich information, it will also introduce redundant and useless information. To tackle this problem, in this paper, we propose a Lightweight Dense Connected Approach with Attention for Single Image Super-Resolution (LDCASR), which employs the attention mechanism to extract useful information in channel dimension. Particularly, we propose the recursive dense group (RDG), consisting of Dense Attention Blocks (DABs), which can obtain more significant representations by extracting deep features with the aid of both dense connections and the attention module, making our whole network attach importance to learning more advanced feature information. Additionally, we introduce the group convolution in DABs, which can reduce the number of parameters to 0.6 M. Extensive experiments on benchmark datasets demonstrate the superiority of our proposed method over five chosen SISR methods.

Sign in / Sign up

Export Citation Format

Share Document