A Novel Collaboration Representation Method of Combining PCANet with Occlusion Positioning for Non-cooperative Face Recognition
DOI:
https://doi.org/10.13052/jwe1540-9589.2513Keywords:
Collaborative representation, face classification, occlusion positioning, local “depth” featuresAbstract
At present, many researches on non-cooperative face recognition have achieved good results, but the representation ability of facial features still needs to be improved. Moreover, due to the existence of occlusion in test samples and the uncertainty of their locations, the task of face recognition is more challenging. To this end, (1) In this paper, multi-scale sample information is added to PCA Network (PCA Network) to obtain Multi-Scale PCANet(MSPCANet) to improve the expression ability of features, and further provide the criteria for selecting the optimal size of PCA filter. (2) The authors use the Markov random field to locate the occlusion position of the test sample, remove the feature information corresponding to the occlusion position in the original image from the feature map, and reduce the information interference caused by the occlusion by classifying the feature information excluding the occlusion. In order to verify the effectiveness of the method, uncoordinated face recognition experiments were carried out on AR and LFW data sets respectively. The results showed that the method with occlusion position information and multi-scale feature information fusion always achieved encouraging performance.
Downloads
References
Esther Bonacker. Perturbed Projection Methods in Convex Optimization – Applied to Radiotherapy Planning. PhD thesis, Kaiserslautern University of Technology, Germany, 2020.
Sijia Cai, Wangmeng Zuo, Lei Zhang, Xiangchu Feng, and Ping Wang. Support vector guided dictionary learning. In David J. Fleet, Tomás Pajdla, Bernt Schiele, and Tinne Tuytelaars, editors, Computer Vision – ECCV 2014 – 13th European Conference, Zurich, Switzerland, September 6–12, 2014, Proceedings, Part IV, volume 8692 of Lecture Notes in Computer Science, pages 624–639. Springer, 2014.
Tsung-Han Chan, Kui Jia, Shenghua Gao, Jiwen Lu, Zinan Zeng, and Yi Ma. Pcanet: A simple deep learning baseline for image classification? IEEE Trans. Image Process., 24(12):5017–5032, 2015.
Jie Chen, Shiguang Shan, Chu He, Guoying Zhao, Matti Pietikäinen, Xilin Chen, and Wen Gao. WLD: A robust local image descriptor. IEEE Trans. Pattern Anal. Mach. Intell., 32(9):1705–1720, 2010.
Hongmei Chi, Haifeng Xia, Lifang Zhang, Chunjiang Zhang, and Xin Tang. Competitive and collaborative representation for classification. Pattern Recognition Letters, 132:46–55, 2020.
Hazim Kemal Ekenel and Rainer Stiefelhagen. Why is facial occlusion a challenging problem? In Massimo Tistarelli and Mark S. Nixon, editors, Advances in Biometrics, Third International Conference, ICB 2009, Alghero, Italy, June 2–5, 2009. Proceedings, volume 5558 of Lecture Notes in Computer Science, pages 299–308. Springer, 2009.
Gary B. Huang, Marwan Mattar, Tamara Berg, and Erik Learned-Miller. Labeled faces in the wild: a database for studying face recognition in unconstrained environments.
Antoine Lesage-Landry, Iman Shames, and Joshua A. Taylor. Predictive online convex optimization. Autom., 113:108771, 2020.
Xiaoxin Li and Ronghua Liang. A review for face recognition with occlusion: From subspace regression to deep learning. Chinese Journal of Computers, 041(001):177–207, 2018.
AM Martinez and R Benavente. The ar face database.
Yi Sun, Xiaogang Wang, and Xiaoou Tang. Deeply learned face representations are sparse, selective, and robust. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, MA, USA, June 7–12, 2015, pages 2892–2900. IEEE Computer Society, 2015.
Xingjie Wei, Chang-Tsun Li, and Yongjian Hu. Robust face recognition under varying illumination and occlusion considering structured sparsity. In 2012 International Conference on Digital Image Computing Techniques and Applications, DICTA 2012, Fremantle, Australia, December 3–5, 2012, pages 1–7. IEEE, 2012.
John Wright, Allen Y. Yang, Arvind Ganesh, Shankar S. Sastry, and Yi Ma. Robust face recognition via sparse representation. IEEE Trans. Pattern Anal. Mach. Intell., 31(2):210–227, 2009.
Huosheng Xie, Yafeng Zhang, and Zesen Wu. Fabric defect detection method combing image pyramid and direction template. IEEE Access, 7:182320–182334, 2019.
Meng Yang and Lei Zhang. Gabor feature based sparse representation for face recognition with gabor occlusion dictionary. In Kostas Daniilidis, Petros Maragos, and Nikos Paragios, editors, Computer Vision – ECCV 2010 – 11th European Conference on Computer Vision, Heraklion, Crete, Greece, September 5–11, 2010, Proceedings, Part VI, volume 6316 of Lecture Notes in Computer Science, pages 448–461. Springer, 2010.
Meng Yang, Lei Zhang, Xiangchu Feng, and David Zhang. Fisher discrimination dictionary learning for sparse representation. In Dimitris N. Metaxas, Long Quan, Alberto Sanfeliu, and Luc Van Gool, editors, IEEE International Conference on Computer Vision, ICCV 2011, Barcelona, Spain, November 6–13, 2011, pages 543–550. IEEE Computer Society, 2011.
Meng Yang, Lei Zhang, Simon Chi-Keung Shiu, and David Zhang. Robust kernel representation with statistical local features for face recognition. IEEE Trans. Neural Networks Learn. Syst., 24(6):900–912, 2013.
Meng Yang, Lei Zhang, Jian Yang, and David Zhang. Metaface learning for sparse representation based face recognition. In Proceedings of the International Conference on Image Processing, ICIP 2010, September 26-29, Hong Kong, China, pages 1601–1604. IEEE, 2010.
Lei Zhang, Meng Yang, and Xiangchu Feng. Sparse representation or collaborative representation: Which helps face recognition? In Dimitris N. Metaxas, Long Quan, Alberto Sanfeliu, and Luc Van Gool, editors, IEEE International Conference on Computer Vision, ICCV 2011, Barcelona, Spain, November 6–13, 2011, pages 471–478. IEEE Computer Society, 2011.
Zihan Zhou, Andrew Wagner, Hossein Mobahi, John Wright, and Yi Ma. Face recognition with contiguous occlusion using markov random fields. In IEEE 12th International Conference on Computer Vision, ICCV 2009, Kyoto, Japan, September 27–October 4, 2009, pages 1050–1057. IEEE Computer Society, 2009.
