Low-resolution degradation face recognition over long distance based on CCA

Wang, Zhenyu; Yang, Wankou; Ben, Xianye

doi:10.1007/s00521-015-1834-y

Cited by 20 publications

(8 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They introduced a tensor analysis to handle rough facial landmark localization in the low-resolution uncontrolled probe images for computing the features. Wang et al [113] treated the LR and HR images as two different groups of variables, and used CCA to determine the transform between them. They then project the LR and HR images to the common linear space which effectively solved the dimensional mismatching problem.…”

Section: Methodsmentioning

confidence: 99%

Face Recognition in Low Quality Images: A Survey

Li¹,

Prieto²,

Mery³

et al. 2018

Preprint

View full text Add to dashboard Cite

Low-quality face recognition (LQFR) has received increasing attention over the past few years. There are numerous potential uses for systems with LQFR capability in real-world environments when high-resolution or high-quality images are difficult or impossible to capture. One of the significant potential application domains for LQFR systems is video surveillance. As the number of surveillance cameras increases (especially in urban environments), the videos that they capture will need to be processed automatically. However, those videos are usually captured with large standoffs, challenging illumination conditions, and diverse angles of view. Faces in these images are generally small in size. Past work on this topic has employed techniques such as super-resolution processing, deblurring, or learning a relationship between different resolution domains. In this paper, we provide a comprehensive review of approaches to low-quality face recognition in the past six years. First, a general problem definition is given, followed by a systematic analysis of the works on this topic by category. Next, we highlight the relevant data sets and summarize their respective experimental results. Finally, we discuss the general limitations and propose priorities for future research.

show abstract

Section: Methodsmentioning

confidence: 99%

Face Recognition in Low Quality Images: A Survey

Li¹,

Prieto²,

Mery³

et al. 2018

Preprint

View full text Add to dashboard Cite

show abstract

“…We follow the experiment setting provided in [73] and [59] and study both closed-set and open-set scenarios. For closed-set evaluation, 180 subjects are used and for open set evaluation, we compare our result with the performance reported in [59] with the HD-1m HD-2.6m HD-4.7m SCface [14] 6.18% 6.18% 1.82% CLPM [35] 3.08% 4.32% 3.46% SSR [82] 18.09% 13.2% 7.04% CSCDN [75] 18.97% 13.58% 6.99% CCA [76] 20.69% 14.85% 9.79% DCA [16] 25.53% 18.44% 12.19% C-RSDA [11] 18.46% 18.08% 15.77% Centerloss [77] [35] 29.12% SDA [91] 40.08% CMFA [64] 39.56% Coupled mapping method [63] 43.24% LMCM [87] 60.40% Centerloss [77] D. Low-resolution face re-identification In this section, we explore LR face re-identification and evaluate it on several datasets captured in an unconstrained environment. We employ the VBOLO dataset for an in-depth study and the SCface, UCCSface, and MegaFace challenge 2 LR subset for other topical explorations.…”

Section: Low-resolution Face Identificationmentioning

confidence: 99%

“…We follow the experiment setting provided in [73] and [59] and study both closed-set and open-set scenarios. For closed-set evaluation, 180 subjects are used and for open set evaluation, we compare our result with the performance reported in [59] with the TABLE II: Experiment 1:Rank-1 rate on SCface with HD and three standoff distances Method HD-1m HD-2.6m HD-4.7m SCface [14] 6.18% 6.18% 1.82% CLPM [35] 3.08% 4.32% 3.46% SSR [82] 18.09% 13.2% 7.04% CSCDN [75] 18.97% 13.58% 6.99% CCA [76] 20.69% 14.85% 9.79% DCA [16] 25.53% 18.44% 12.19% C-RSDA [11] 18.46% 18.08% 15.77% Centerloss [77] [35] 29.12% SDA [91] 40.08% CMFA [64] 39.56% Coupled mapping method [63] 43.24% LMCM [87] 60.40% Centerloss [77](ours) 69.60% LMSoftmax [43](ours) 40.4% AMSoftmax [72](ours) 46.8% L2softmax [57](ours) 42.8% defined openness at 14.11 percent. When looking at the result of the closed-set evaluation, our method beats the UCCS baseline by nearly 20 percent on rank-1 accuracy and also outperforms the DNN method in [73] by nearly 35 percent on rank-1 rate under the same training and evaluation protocol.…”

Section: Low-resolution Face Identificationmentioning

confidence: 99%

On Low-Resolution Face Recognition in the Wild: Comparisons and New Techniques

Prieto

Mery

et al. 2019

IEEE Trans.Inform.Forensic Secur.

145

View full text Add to dashboard Cite

Although face recognition systems have achieved impressive performance in recent years, the low-resolution face recognition task remains challenging, especially when the lowresolution faces are captured under non-ideal conditions, as is common in surveillance-based applications. Faces captured in such conditions are often contaminated by blur, non-uniform lighting, and non-frontal face pose. In this paper, we analyze face recognition techniques using data captured under lowquality conditions in the wild. We provide a comprehensive analysis of experimental results for two of the most important applications in real surveillance applications, and demonstrate practical approaches to handle both cases that show promising performance. The following three contributions are made: (i) we conduct experiments to evaluate super-resolution methods for low-resolution face recognition; (ii) we study face re-identification on various public face datasets including real surveillance and low-resolution subsets of large-scale datasets, present a baseline result for several deep learning based approaches, and improve them by introducing a Generative Adversarial Network (GAN) pre-training approach and fully convolutional architecture; and (iii) we explore low-resolution face identification by employing a state-of-the-art supervised discriminative learning approach. Evaluations are conducted on challenging portions of the SCface and UCCSface datasets.

show abstract

“…al. [12] presented Canonical correlation analysis (CCA). In CCA LR and HR image features with minimum deviation is extracted.…”

Section: Fig 1: Block Diagram Of Lr-frmentioning

confidence: 99%

Low Resolution Face Recognition System Performance for Basic Feature Space Methods with Various Illumination Normalization Techniques

Kapse*,

Kumar

2019

IJITEE

View full text Add to dashboard Cite

The Face recognition research identified with the field of automated surveillance systems in real life application has pulled in more consideration today with extensive use of vision cameras in biometrics and surveillance applications, globally. The small size images or poor quality images are generally Low Resolution images. Authenticating faces, with variation in pose, illumination, disguise and more, from such Low-resolution images, is the main purpose of Low Resolution Face Recognition (LR FR) system. We have assessed the LR FR system for various basic feature space techniques like PCA, LDA and Fisherface. Different illumination normalization techniques are applied on the cropped Yale face database prior to feature extraction and identification. In our work the low-resolution images, of size 32x32, are the down-sampled versions high-resolution facial images from cropped Yale face database. Our experiment demonstrates the encouraging performance, with recognition accuracy as 97.43%, on Low Resolution, Low quality face images.

show abstract

Low-resolution degradation face recognition over long distance based on CCA

Cited by 20 publications

References 20 publications

Face Recognition in Low Quality Images: A Survey

Face Recognition in Low Quality Images: A Survey

On Low-Resolution Face Recognition in the Wild: Comparisons and New Techniques

Low Resolution Face Recognition System Performance for Basic Feature Space Methods with Various Illumination Normalization Techniques

Contact Info

Product

Resources

About