Lower Resolution Face Recognition in Surveillance Systems Using Discriminant Correlation Analysis

@article{Haghighat2017LowerRF,
  title={Lower Resolution Face Recognition in Surveillance Systems Using Discriminant Correlation Analysis},
  author={Mohammad Haghighat and Mohamed Abdel-Mottaleb},
  journal={2017 12th IEEE International Conference on Automatic Face \& Gesture Recognition (FG 2017)},
  year={2017},
  pages={912-917}
}
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… 
View on IEEE
doi.org
41 Citations
Highly Influential Citations
2
Background Citations
14
Methods Citations
10

Figures and Tables from this paper

41 Citations

Face Recognition in Low Quality Images: A Survey
TLDR
A comprehensive review of approaches to low-resolution face recognition in the past five years is provided and the general limitations are summarized and speculate a priorities for the future effort.
Face Recognition in LowQuality Images: A Survey
TLDR
A comprehensive review of approaches to low-quality face recognition in the past six years is provided, followed by a systematic analysis of the works on this topic by category.
Lightweight Low-Resolution Face Recognition for Surveillance Applications
TLDR
Inspired by the compactness and computation efficiency of lightweight deep face networks and their high accuracy on general face recognition tasks, this work proposes to benchmark two recently introduced lightweight face models on low-resolution surveillance imagery to enable efficient system deployment.
Robust Face Recognition Using Sparse and Dense Hybrid Representation with Local Correlation
TLDR
Experimental analysis shows that performance of the proposed Face Recognition system based on a combination of Sparse and Dense representation (SDR) along with Local Correlation is better than the state-of-art face recognition approaches and the performance gains are very high.
Unsupervised Face Domain Transfer for Low-Resolution Face Recognition
TLDR
A novel unsupervised face domain transfer for robust low-resolution face recognition is proposed and the complementarity between generative face augmentation at image-level and spatial resolution adaptation at feature-level is demonstrated.
QDF: A face database with varying quality
Enhancing Low Quality Face Image Matching by Neurovisually Inspired Deep Learning
TLDR
The current work demonstrates not only better detection of low quality face images in NFGS enabled deep learning framework, but also it prescribes an efficient way ofLow quality face image matching addressing low contrast, low resolution and motion blur which are prime responsible factors of making image low quality.
IPU-Net: Multi Scale Identity-Preserved U-Net for Low Resolution Face Recognition
TLDR
This work proposes an identity-preserved U-Net which is capable of super-resolving very low resolution faces to their high resolution counterparts while preserving identity-related information, and outperforms competing super resolution and low resolution face recognition methods.
Hierarchical Deep CNN Feature Set-Based Representation Learning for Robust Cross-Resolution Face Recognition
TLDR
A feature set-based representation learning (FSRL) scheme to collaboratively represent the hierarchical features for more accurate recognition and the superiority of the presented algorithm to the other competitive CRFR approaches is verified.
Image set-based face recognition using pose estimation with facial landmarks
TLDR
This study presents a method to estimate the poses of image set by applying nonlinear least squares to facial landmarks and improves the conventional PnP method by identifying a frontal image of each image set instead of using a fixed 3-D model.
...
...

References

SHOWING 1-10 OF 27 REFERENCES
Pose-robust recognition of low-resolution face images
TLDR
This paper develops a completely automatic, novel approach for matching surveillance quality facial images to high-resolution images in frontal pose, which are often available during enrollment, and shows the usefulness of the proposed approach for the application of tracking and recognition in surveillance videos.
Pose-robust recognition of low-resolution face images
TLDR
A novel approach for matching surveillance quality facial images to high resolution images in frontal pose which are often available during enrollment is developed and uses Multidimensional Scaling to simultaneously transform the features from the poor quality probe images and the high quality gallery images in such a manner that the distances between them approximate the distances had the probe images been captured in the same conditions as the gallery images.
Multidimensional Scaling for Matching Low-Resolution Face Images
TLDR
The proposed approach for matching low-resolution probe images with higher resolution gallery images, which are often available during enrollment, using Multidimensional Scaling (MDS), improves the matching performance significantly as compared to performing matching in the low- resolution domain or using super-resolution techniques to obtain a higher resolution test image prior to recognition.
Very low resolution face recognition problem
  • W. W. Zou, P. Yuen
  • Computer Science
    2010 Fourth IEEE International Conference on Biometrics: Theory, Applications and Systems (BTAS)
  • 2010
TLDR
Experimental results show that the proposed method outperforms the existing methods, in terms of image quality and recognition accuracy, as well as face super-resolution methods.
Simultaneous super-resolution and feature extraction for recognition of low-resolution faces
TLDR
This work proposes a new procedure for recognition of low-resolution faces, when there is a high-resolution training set available, and shows that recognition of faces of as low as 6 times 6 pixel size is considerably improved compared to matching using a super-resolution reconstruction followed by classification, and to matching with a low- resolution training set.
Low-resolution degradation face recognition over long distance based on CCA
TLDR
This work uses canonical correlation analysis to extract the correlation between high-resolution face images and low-resolution ones and to find the transform pair between them, and shows that face images of the same individual with variable resolutions can be matched accurately.
Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection
TLDR
A face recognition algorithm which is insensitive to large variation in lighting direction and facial expression is developed, based on Fisher's linear discriminant and produces well separated classes in a low-dimensional subspace, even under severe variations in lighting and facial expressions.
Learning-based face hallucination in DCT domain
  • Wei Zhang, W. Cham
  • Computer Science
    2008 IEEE Conference on Computer Vision and Pattern Recognition
  • 2008
TLDR
A method to infer AC coefficients by introducing an efficient learning-based inference model is proposed, which can recover the high-resolution face image from a single low-resolution one and can lead to significant savings in memory and computation cost.
Generalized Face Super-Resolution
  • K. Jia, S. Gong
  • Computer Science
    IEEE Transactions on Image Processing
  • 2008
TLDR
An automatic face alignment algorithm capable of pixel-wise alignment by iteratively warping the probing face to its projection in the space of training face images and novelty of the approach in coping with multimodal hallucination and its robustness in automatic alignment under practical imaging conditions are presented.
Eigenfaces for Recognition
TLDR
A near-real-time computer system that can locate and track a subject's head, and then recognize the person by comparing characteristics of the face to those of known individuals, and that is easy to implement using a neural network architecture.
...
...