7,030 Hits in 5.3 sec

Low-Resolution Face Recognition via Sparse Representation of Patches

Liansheng Zhuang, Mengliao Wang, Wen Yu, Nenghai Yu, Yangchun Qian
2009 2009 Fifth International Conference on Image and Graphics  
Then, we find the sparse representation of these patches based on corresponding LBP features of high-resolution face image patches.  ...  Images resolution plays an important role during face recognition. Low-resolution face images will reduce drastically the performance of face recognition algorithms.  ...  Face Recognition via Sparse Representation of Patches The task of low-resolution face recognition requires us to classify a given low-resolution face image, according to the given gallery which is made  ... 
doi:10.1109/icig.2009.154 dblp:conf/icig/ZhuangWYYQ09 fatcat:sqm2radfifewtm3edi37kiahki

Face hallucination VIA sparse coding

Jianchao Yang, Hao Tang, Yi Ma, Thomas Huang
2008 2008 15th IEEE International Conference on Image Processing  
In this paper, we address the problem of hallucinating a high resolution face given a low resolution input face. The problem is approached through sparse coding.  ...  To further enhance the detailed facial information, we propose a local patch method based on sparse representation with respect to coupled overcomplete patch dictionaries, which can be fast solved through  ...  Suppose we have low-resolution face images {I (1) , ..., x (N ) ], where y (i) is the vector representation of the i-th low resolution patch, and x (i) is the vector representation of the corresponding  ... 
doi:10.1109/icip.2008.4711992 dblp:conf/icip/YangTMH08 fatcat:vaek5iaesfgxravuqh4ezw225e

Enhancing face recognition at a distance using super resolution

Nadia AL-Hassan, Sabah A. Jassim, Harin Sellahewa
2012 Proceedings of the on Multimedia and security - MM&Sec '12  
Recent works have used SR as a pre-processing step to overcome the problem of low-resolution images in face recognition.  ...  The proposed method is evaluated on database of high and low-resolution images-Extended Yale B database and UBHSD database-and for face recognition at a distance.  ...  This SR approach can be justified by the assumption that a low-resolution image, or an image patch, is a sparse representation of a high-resolution image/patch.  ... 
doi:10.1145/2361407.2361429 dblp:conf/mmsec/Al-HassanJS12 fatcat:wvsupm75u5efxdhpx2npio27z4

Face image super-resolution via weighted patches regression

Yiping Zhang, Zhihong Zhang, Guosheng Hu, Edwin R. Hancock
2016 2016 23rd International Conference on Pattern Recognition (ICPR)  
ACKNOWLEDGMENT This work is supported by National Natural Science Foundation of China (Grant No.61402389).  ...  INTRODUCTION One of the most common challenges to practical face recognition system is that most face images captured in the wild are of low resolutions.  ...  Super-resolution via Couple Dictionaries and Sparse Coding Yang et al. [9] proposed an approach for super-resolution based on sparse representation.  ... 
doi:10.1109/icpr.2016.7900242 dblp:conf/icpr/ZhangZHH16 fatcat:zozjfo5hebcivppuswhxqb7kwq

Sparse Representation-Based Super Resolution for Face Recognition At a Distance

Emil Bilgazyev, Boris Efraty, Shishir Shah, Ioannis Kakadiaris
2011 Procedings of the British Machine Vision Conference 2011  
All statements of fact, opinion or conclusions contained herein are those of the authors and should not be construed as representing the official views or policies of IARPA, the ODNI, the U.S.  ...  by the University of Houston (UH) Eckhard Pfeiffer Endowment Fund.  ...  We compared the proposed DT-CWT-based SR method (UHSR) with the following SR algorithms: bicubic interpolation (BCI), Simultaneous Super Resolution and Recognition (S2R2) [6] , and SR via Sparse Representation  ... 
doi:10.5244/c.25.52 dblp:conf/bmvc/BilgazyevESK11 fatcat:yoexq4tghvek3ivbtqi7tijrwu

MagnifyMe: Aiding Cross Resolution Face Recognition via Identity Aware Synthesis [article]

Maneet Singh, Shruti Nagpal, Richa Singh, Mayank Vatsa, Angshul Majumdar
2018 arXiv   pre-print
In this research, we propose Synthesis via Deep Sparse Representation algorithm for synthesizing a high resolution face image from a low resolution input image.  ...  Enhancing low resolution images via super-resolution or image synthesis for cross-resolution face recognition has been well studied.  ...  This leads to the key contribution of this work: Synthesis via Deep Sparse Representation (SDSR), a transfer learning approach for synthesizing a high resolution image for a given low resolution input.  ... 
arXiv:1802.08057v1 fatcat:47fhj3f675d3ngomhog6jrzetm

Identity Aware Synthesis for Cross Resolution Face Recognition

Maneet Singh, Shruti Nagpal, Mayank Vatsa, Richa Singh, Angshul Majumdar
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
Enhancing low resolution images via super-resolution or synthesis algorithms for cross-resolution face recognition has been well studied.  ...  In this research, we propose Synthesis via Hierarchical Sparse Representation (SHSR) algorithm for synthesizing a high resolution face image from a low resolution input image.  ...  This research is partially supported by MEITY (Government of India). M. Vatsa and R. Singh are partially supported through Infosys Center for Artificial Intelligence, IIIT-Delhi. S.  ... 
doi:10.1109/cvprw.2018.00089 dblp:conf/cvpr/SinghNV0M18 fatcat:oye5ufjtprbbne6nl5zhc32tom

A Boosting Method to Face Image Super-resolution [article]

Shanjun Mao, Da Zhou, Yiping Zhang, Zhihong Zhang, Jingjing Cao
2018 arXiv   pre-print
Recently sparse representation has gained great success in face image super-resolution.  ...  The conventional sparsity-based methods enforce sparse coding on face image patches and the representation fidelity is measured by ℓ_2-norm.  ...  algorithm via AdaBoost In sparse coding, for each low-resolution patches A i , we use the equatz to obtain its corresponding sparse representation, and we write these equations together: α = arg min α  ... 
arXiv:1609.01805v3 fatcat:x5ewoomc7vfdvg5oftf6t37c4e

Image super-resolution as sparse representation of raw image patches

Jianchao Yang, John Wright, Thomas Huang, Yi Ma
2008 2008 IEEE Conference on Computer Vision and Pattern Recognition  
The low-resolution image is viewed as downsampled version of a high-resolution image, whose patches are assumed to have a sparse representation with respect to an over-complete dictionary of prototype  ...  representation is sparse and the recovered high-resolution image is competitive or even superior in quality to images produced by other SR methods.  ...  We regularize the problem via the following prior on small patches x of X: Sparse representation prior.  ... 
doi:10.1109/cvpr.2008.4587647 dblp:conf/cvpr/YangWHM08 fatcat:crpeh7lwxvfgnjud3z2fbkfrwm

A Review of Various Approaches to Face Hallucination

Ms. Prachi Autee, Mr. Samyak Mehta, Ms. Sampada Desai, Vinaya Sawant, Anuja Nagare
2015 Procedia Computer Science  
In this paper we have analysed various approaches for enhancing low-resolution images namely, Face Hallucination (FH) with Sparse Representation, FH using Eigentransformation, FH via Locality Constraint  ...  The numerous applications of this method include in the field of image enhancement, face recognition surveillance and security.  ...  Face Hallucination using sparse representation works more efficiently when it is applied to low-resolution facial images extracted from surveillance footage.  ... 
doi:10.1016/j.procs.2015.03.162 fatcat:bubmz5njjjc73nq6fnffguepwq

Multi-Layer Sparse Representation for Weighted LBP-Patches Based Facial Expression Recognition

Qi Jia, Xinkai Gao, He Guo, Zhongxuan Luo, Yi Wang
2015 Sensors  
Especially for low intensity expression, most of the existing training methods have quite low recognition rates.  ...  Deriving an effective facial representation from original face images is a vital step for successful facial expression recognition.  ...  Author Contributions Qi Jia conceived and designed the experiments and wrote part of the paper. Xinkai Gao performed the experiments and also wrote part of the paper.  ... 
doi:10.3390/s150306719 pmid:25808772 pmcid:PMC4435128 fatcat:ohttyfbvkfdurghijjqljomgl4

Face Hallucination: A Review

Jaskiran Kaur, Asst. Prof. Manish Mahajan
2014 International Journal of Engineering Trends and Technoloy  
For addressing the problem of hallucinating a higher resolution face given a low resolution input face, the goal of face hallucination aim should be to produce high resolution images with fidelity from  ...  low-resolution ones.  ...  They have addressed the problem of hallucination of a high resolution face given a low resolution input picture. This problem is processed through sparse coding.  ... 
doi:10.14445/22315381/ijett-v11p212 fatcat:pmdicmlewbfjjaqffxlx36rvjq

A Survey on Various Single Image Super Resolution Techniques

A.Haza rathaiah
2013 International Journal of Innovative Research in Science, Engineering and Technology  
The main aim of super resolution (SR) is to increase better visual quality of available low resolution image.  ...  Superresolution is the process of recovering a high-resolution (HR) image from single image or multiple low-resolution (LR) images of the same scene .  ...  / 2015 Integrated Single Image Super Resolution Based on Sparse Representation [2] Integrated method using dictionary of patches and sparse representation -Uses linear combination of low  ... 
doi:10.15680/ijirset.2012.0102024 fatcat:t45xr2uapvcrdnzds7ldc37eta

Face Recognition in Low Quality Images: A Survey [article]

Pei Li, Loreto Prieto, Domingo Mery, Patrick Flynn
2019 arXiv   pre-print
Low-resolution face recognition (LRFR) has received increasing attention over the past few years.  ...  We further address the related works on unconstrained low-resolution face recognition and compare them with the result that use synthetic low-resolution data.  ...  They combined restoration and recognition in a unified framework by seeking sparse representation over the training faces via l1 norm minimization.  ... 
arXiv:1805.11519v3 fatcat:izpl554u3fga5d62e6jxw4zuwu

Discriminative Face Hallucination via Locality-Constrained and Category Embedding Representation

Licheng Liu, Rushi Lan, Yaonan Wang
2020 IEEE Transactions on Systems, Man & Cybernetics. Systems  
This article proposes a locality-constrained and category embedding representation (LCER) method to super-resolve face image in a supervised manner by embedding the label information in data representation  ...  Recent years have witnessed the rapid development of face image hallucination techniques.  ...  The low-resolution problem will severely degrade the performance of the recognition system.  ... 
doi:10.1109/tsmc.2020.2965572 fatcat:cttonyzw5rbglkpsjjm7gsba54
« Previous Showing results 1 — 15 out of 7,030 results