An Efficient Non-Occluded Face Area Detection Method under Unconstrained Environment of Smartphone Database

Occlusion is one of the most challenging problems for recognizing faces captured in unconstrained conditions. This paper focuses on direct detect the useful part in the face which used for features extraction process. To solve occlusion problem and detect un occluded face parts, a Non-Occluded Face Area Detection (NOFAD) method based on geometric features is proposed. The performance of the proposed method is evaluated on the SFV and MOBIO databases, and the experimental results show the outperformance of the proposed method in extracting the non-occluded facial area, realising an accuracy rate of 99.4% and 99.1%, respectively.

[1]  P. V. G. D. Prasad Reddy,et al.  Skin based Occlusion Detection and Face Recognition using Machine Learning Techniques , 2012 .

[2]  Matti Pietikäinen,et al.  Bi-Modal Person Recognition on a Mobile Phone: Using Mobile Phone Data , 2012, 2012 IEEE International Conference on Multimedia and Expo Workshops.

[3]  Allen Y. Yang,et al.  Robust Face Recognition via Sparse Representation , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Fatimah Khalid,et al.  A Robust Geometric Skin Colour Face Detection Method under Unconstrained Environment of Smartphone Database , 2019, Applied Mechanics and Materials.

[5]  Xinge You,et al.  Robust face recognition via occlusion dictionary learning , 2014, Pattern Recognit..

[6]  Yi-Ping Hung,et al.  Distinctive Personal Traits for Face Recognition Under Occlusion , 2006, 2006 IEEE International Conference on Systems, Man and Cybernetics.

[7]  Tejas I. Dhamecha,et al.  Recognizing Disguised Faces: Human and Machine Evaluation , 2014, PloS one.

[8]  K. G. Subramanian,et al.  Recognizing occluded faces by exploiting psychophysically inspired similarity maps , 2013, Pattern Recognit. Lett..

[9]  Jianhua Hou,et al.  Face recognition with contiguous occlusion based on image segmentation , 2014, 2014 International Conference on Audio, Language and Image Processing.

[10]  Rubén San-Segundo-Hernández,et al.  A survey on techniques to handle face recognition challenges: occlusion, single sample per subject and expression , 2017, Artificial Intelligence Review.

[11]  Marios Savvides,et al.  Semi self-training beard/moustache detection and segmentation simultaneously , 2017, Image Vis. Comput..

[12]  K. S. Patnaik,et al.  Occlusion invariant face recognition system , 2016, 2016 World Conference on Futuristic Trends in Research and Innovation for Social Welfare (Startup Conclave).

[13]  Ling Shao,et al.  Face recognition with a small occluded training set using spatial and statistical pooling , 2018, Inf. Sci..

[14]  Koichi Ito,et al.  Performance improvement of face recognition algorithms using occluded-region detection , 2013, 2013 International Conference on Biometrics (ICB).