Application of robust face recognition in video surveillance systems

Abstract

In this paper, we propose a video searching system that utilizes face recognition as searching indexing feature. As the applications of video cameras have great increase in recent years, face recognition makes a perfect fit for searching targeted individuals within the vast amount of video data. However, the performance of such searching depends on the quality of face images recorded in the video signals. Since the surveillance video cameras record videos without fixed postures for the object, face occlusion is very common in everyday video. The proposed system builds a model for occluded faces using fuzzy principal component analysis (FPCA), and reconstructs the human faces with the available information. Experimental results show that the system has very high efficiency in processing the real life videos, and it is very robust to various kinds of face occlusions. Hence it can relieve people reviewers from the front of the monitors and greatly enhances the efficiency as well. The proposed system has been installed and applied in various environments and has already demonstrated its power by helping solving real cases.

References

[1] ZhaoW., ChellappaR., PhillipsP.J., RosenfeldA.. ACM Computing Surveys, 2003, 35: 399

[2] SolankiK., PittaliaP.. International Journal of Computer Applications, 2016, 133: 20

[3] ZhangH.. A Multi-model Biometric Image Acquisition System, Biometric Recognition, 2015,

[4] ChengL., WangJ., GongY.. Robust Deep Auto-encoder for Occluded Face Recognition, ACM International Conference on Multimedia, 2015, 1099

[5] PadovaniS., TepperM., Jacobo-BerllesJ.. Pattern Recognition Letters, 2014, 36: 235

[6] OuW., LuanX., GouJ.. Robust Discriminative Nonnegative Dictionary Learning for Occluded Face Recognition, Pattern Recognition Letters, 2017,

[7] ZhouB., LapedrizaA., KhoslaA., OlivaA., TorralbaA.. IEEE Transactions on Pattern Analysis & Machine Intelligence PP, 2017, 1

[8] YangA. Y.. Fast ℓ1-minimization Algorithms and an Application in Robust Face Recognition: A Review, IEEE International Conference on Image Processing, 2010, 1849

[9] YangY., LovellB. C., DadgostarF.. Content-Based Video Retrieval (CBVR) System for CCTV Surveillance Videos, Digital Image Computing: Techniques and Applications, 2010, 183

[10] SharmaS.. Applied Multivariate Techniques, J. Wiley, 1996, 100

[11] PartridgeM., JabriM.. Journal of the ACM, 2011, 58: 1

[12] HeE. J., FernandezJ. A., KumarB. V. K. V.. Masked Correlation Filters for Partially Occluded Face Recognition, IEEE ICASSP, 2016, 1293

[13] WiskottL.. IEEE Transactions on Pattern Analysis & Machine Intelligence, 1997, 19: 775

[14] HochulS., Seong-DaeK., Hae-ChulC.. Pattern Recognition Letters, 2007, 28: 1077

[15] YamborW. S.. Analyzing PCA-based Face Recognition Algorithms: Eigenvector Selection and Distance Measures, All Publications, 2002, 39

[16] HanP. Y., JinA. T. B., SiongL. H.. Discrete Dynamics in Nature and Society, 2011, 2011: 701