光电子快报(英文版), 2018, 14 (2): 152, Published Online: Sep. 17, 2018  

Application of robust face recognition in video surveil-lance systems

Author Affiliations
1 Tianjin ISecure Technologies Co. Ltd, Tianjin 300457, China
2 School of Electronic and Information Engineering, Ningbo University of Technology, Ningbo 315211, China
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 oc-cluded 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 moni-tors and greatly enhances the efficiency as well. The proposed system has been installed and applied in various envi-ronments and has already demonstrated its power by helping solving real cases.
References

[1] Zhao W, Chellappa R, Phillips PJ and Rosenfeld A, ACM Computing Surveys 35, 399 (2003).

[2] Solanki K and Pittalia P, International Journal of Com-puter Applications 133, 20 (2016).

[3] Zhang Haoxiang, A Multi-model Biometric Image Ac-quisition System, Biometric Recognition, Springer In-ternational Publishing, 2015.

[4] Cheng L, Wang J and Gong Y, Robust Deep Auto-encoder for Occluded Face Recognition, ACM International Conference on Multimedia, 1099 (2015).

[5] Padovani S., Tepper M. and Jacobo-Berlles J., Pattern Recognition Letters 36, 235 (2014).

[6] Ou W, Luan X and Gou J, Robust Discriminative Non-negative Dictionary Learning for Occluded Face Rec-ognition, Pattern Recognition Letters, Available online 17 July 2017.

[7] Zhou B., Lapedriza A., Khosla A., Oliva A. and Tor-ralba A., IEEE Transactions on Pattern Analysis & Ma-chine Intelligence PP, 1-1 (2017).

[8] Yang A. Y, Fast .1-minimization Algorithms and an Application in Robust Face Recognition: A Review, IEEE International Conference on Image Processing, 1849 (2010).

[9] Yang Y., Lovell B. C. and Dadgostar F., Content-Based Video Retrieval (CBVR) System for CCTV Surveil-lance Videos, Digital Image Computing: Techniques and Applications, 183 (2010).

[10] Sharma Subhash, Applied Multivariate Techniques, J. Wiley, 100 (1996).

[11] Partridge M. and Jabri M., Journal of the ACM 58, 1 (2011).

[12] He E J, Fernandez J A and Kumar B V K V, Masked Correlation Filters for Partially Occluded Face Recog-nition, IEEE ICASSP, 1293 (2016).

[13] Wiskott L., IEEE Transactions on Pattern Analysis & Machine Intelligence 19, 775 (1997).

[14] Hochul Shin, Seong-Dae Kim and Hae-Chul Choi, Pat-tern Recognition Letters 28, 1077 (2007).

[15] Yambor W. S., Analyzing PCA-based Face Recognition Algorithms: Eigenvector Selection and Distance Meas-ures, All Publications, 39 (2002).

[16] Han P. Y., Jin A. T. B. and Siong L. H., Discrete Dy-namics in Nature and Society 2011, 701 (2011).

ZHANG De-xin, AN Peng, ZHANG Hao-xiang. Application of robust face recognition in video surveil-lance systems[J]. 光电子快报(英文版), 2018, 14(2): 152.

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!