Face recognition in low-resolution surveillance video streams

Face recognition technology has been widely adopted in many mission-critical applications as a means of human identification, controlled admission, E-bank authentication, and mobile device access. Security surveillance is also a growing application for face recognition techniques; however, challenges exist from low resolution (LR) and high noise, multi-angle and multi-distance changes, and different light conditions. In comparison, algorithms applied to cell phone imagery or other specific camera devices mainly function on high resolution images with fixed angles and small changes of illumination. As face recognition in security surveillance becomes more important in the era of dense urbanization, it is essential to develop algorithms that are able to provide satisfactory performance in processing the video frames generated by low resolution surveillance cameras. In this paper, we propose a novel face recognition method that is suitable for low resolution surveillance cameras. The technique is demonstrated on a face dataset generated from real-world surveillance scenarios, from which an end-to-end approach is taken to match high resolution (HR) images with low resolution (LR) images from the surveillance video. The experimental results validate the effectiveness of the novel method that improves the accuracy of face recognition in surveillance security scenarios.

[1]  Xiaogang Wang,et al.  DeepID3: Face Recognition with Very Deep Neural Networks , 2015, ArXiv.

[2]  Heng Yang,et al.  Facial feature point detection: A comprehensive survey , 2014, Neurocomputing.

[3]  Yufeng Zheng,et al.  An Exploration of the Impacts of Three Factors in Multimodal Biometric Score Fusion : Score Modality , Recognition Method , and Fusion Process , 2015 .

[4]  James Philbin,et al.  FaceNet: A unified embedding for face recognition and clustering , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Leslie Lamport,et al.  Latex : A Document Preparation System , 1985 .

[6]  Chengjun Liu,et al.  Gabor feature based classification using the enhanced fisher linear discriminant model for face recognition , 2002, IEEE Trans. Image Process..

[7]  C. H. Chen,et al.  Handbook of Pattern Recognition and Computer Vision , 1993 .

[8]  Ming Yang,et al.  DeepFace: Closing the Gap to Human-Level Performance in Face Verification , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[9]  Mei Wang,et al.  Deep Face Recognition: A Survey , 2018, Neurocomputing.

[10]  Alan Sullivan,et al.  Verification of Very Low-Resolution Faces Using An Identity-Preserving Deep Face Super-Resolution Network , 2019, ArXiv.

[11]  Kenneth M. Hanson,et al.  Introduction to Bayesian image analysis , 1993 .

[12]  Xiaogang Wang,et al.  Deep Learning Face Representation by Joint Identification-Verification , 2014, NIPS.

[13]  M. Turk,et al.  Eigenfaces for Recognition , 1991, Journal of Cognitive Neuroscience.

[14]  Omkar M. Parkhi,et al.  VGGFace2: A Dataset for Recognising Faces across Pose and Age , 2017, 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018).

[15]  N. Metropolis,et al.  Equation of State Calculations by Fast Computing Machines , 1953, Resonance.

[16]  Junjun Jiang,et al.  Noise Robust Face Image Super-Resolution Through Smooth Sparse Representation , 2017, IEEE Transactions on Cybernetics.

[17]  Yann LeCun,et al.  Learning a similarity metric discriminatively, with application to face verification , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[18]  Ronghua Xu,et al.  Real-Time Human Objects Tracking for Smart Surveillance at the Edge , 2018, 2018 IEEE International Conference on Communications (ICC).

[19]  Stephen F. Gull,et al.  Developments in Maximum Entropy Data Analysis , 1989 .

[20]  Heng Su,et al.  Survey of Super-resolution Image Reconstruction Methods: Survey of Super-resolution Image Reconstruction Methods , 2014 .

[21]  Yu Qiao,et al.  A Discriminative Feature Learning Approach for Deep Face Recognition , 2016, ECCV.

[22]  Chang Huang,et al.  Targeting Ultimate Accuracy: Face Recognition via Deep Embedding , 2015, ArXiv.

[23]  Bhiksha Raj,et al.  SphereFace: Deep Hypersphere Embedding for Face Recognition , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[24]  Chin-Tser Huang,et al.  Poster Abstract: Smart Urban Surveillance Using Fog Computing , 2016, 2016 IEEE/ACM Symposium on Edge Computing (SEC).

[25]  Zheng Liu,et al.  Multispectral Image Fusion and Colorization , 2018 .

[26]  Shaogang Gong,et al.  Surveillance Face Recognition Challenge , 2018, ArXiv.

[27]  Su Heng,et al.  Survey of Super-resolution Image Reconstruction Methods , 2013 .

[28]  Azriel Rosenfeld,et al.  Face recognition: A literature survey , 2003, CSUR.

[29]  Matti Pietikäinen,et al.  Face Description with Local Binary Patterns: Application to Face Recognition , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[30]  Ronghua Xu,et al.  Real-Time Human Detection as an Edge Service Enabled by a Lightweight CNN , 2018, 2018 IEEE International Conference on Edge Computing (EDGE).

[31]  H. Refai,et al.  Free-space optical wavelength diversity scheme for fog mitigation in a ground-to-unmanned-aerial-vehicle communications link , 2006 .