Face Occlusion Recognition With Deep Learning in Security Framework for the IoT

Currently, the security of the Internet of Things (IoT) has aroused great concern. Face detection under arbitrary occlusion has become a key problem affecting social security. This paper designs a novel face occlusion recognition framework in the security scene of IOT, which is used to detect some crime behaviors. Our designed framework utilizes the gradient and shape cues in a deep learning model, and it has been demonstrated to be robust for its superiority to detect faces with severe occlusion. Our contributions contain three main aspects: Firstly, we present a new algorithm based on energy function for face detection; Secondly, we use the CNN models to create deep features of occluded face; Finally, to check whether the detected face is occluded, novel sparse classification model with deep learning scheme is constructed. Statistical results demonstrate that, compared with the state of the arts, our algorithm is superior in both accuracy and robustness. Our designed head detection algorithm can achieve 98.89% accuracy rate even though there are various types of severe occlusions in faces, and our designed occlusion verification scheme can achieve 97.25% accuracy rate, at a speed of 10 frames per second.

[1]  Bo Li,et al.  A Fast Face Detection Method via Convolutional Neural Network , 2018, Neurocomputing.

[2]  Hong Jiang,et al.  A communication-reduced and computation-balanced framework for fast graph computation , 2018, Frontiers of Computer Science.

[3]  Zhi-Hua Zhou,et al.  Recognizing partially occluded, expression variant faces from single training image per person with SOM and soft k-NN ensemble , 2005, IEEE Transactions on Neural Networks.

[4]  Jiwu Shu,et al.  Encoding-Aware Data Placement for Efficient Degraded Reads in XOR-Coded Storage Systems: Algorithms and Evaluation , 2018, IEEE Transactions on Parallel and Distributed Systems.

[5]  Alireza Souri,et al.  A systematic review of IoT communication strategies for an efficient smart environment , 2019, Trans. Emerg. Telecommun. Technol..

[6]  Hongjun Jia,et al.  Support Vector Machines in face recognition with occlusions , 2009, CVPR.

[7]  De Xu,et al.  Real-time elliptical head contour detection under arbitrary pose and wide distance range , 2009, J. Vis. Commun. Image Represent..

[8]  Zhengrong Yao,et al.  Tracking a Detected Face with Dynamic Programming , 2004, CVPR Workshops.

[9]  Nikolaos G. Bourbakis,et al.  A survey of skin-color modeling and detection methods , 2007, Pattern Recognit..

[10]  Wenxing Zhu,et al.  Discrete Relaxation Method for Triple Patterning Lithography Layout Decomposition , 2017, IEEE Transactions on Computers.

[11]  Xiangyu Wang,et al.  RF Sensing in the Internet of Things: A General Deep Learning Framework , 2018, IEEE Communications Magazine.

[12]  Hongdong Li,et al.  Contour Completion Without Region Segmentation , 2016, IEEE Transactions on Image Processing.

[13]  Che-Yen Wen,et al.  The mask detection technology for occluded face analysis in the surveillance system. , 2005, Journal of forensic sciences.

[14]  Xiangjian He,et al.  Discriminative Dictionary Learning With Motion Weber Local Descriptor for Violence Detection , 2017, IEEE Transactions on Circuits and Systems for Video Technology.

[15]  Walid Saad,et al.  Deep Learning-Based Dynamic Watermarking for Secure Signal Authentication in the Internet of Things , 2017, 2018 IEEE International Conference on Communications (ICC).

[16]  Tao Zhang,et al.  Collaborative representation based face classification exploiting block weighted LBP and analysis dictionary learning , 2019, Pattern Recognit..

[17]  Yi Zeng,et al.  A Fast Contour Detection Model Inspired by Biological Mechanisms in Primary Vision System , 2018, Front. Comput. Neurosci..

[18]  Yining Liu,et al.  A Secure Authentication Protocol for Internet of Vehicles , 2019, IEEE Access.

[19]  Chien-Ming Chen,et al.  Attacks and solutions on a three-party password-based authenticated key exchange protocol for wireless communications , 2018, Journal of Ambient Intelligence and Humanized Computing.

[20]  Guolong Chen,et al.  Relative influence maximization in competitive social networks , 2017, Science China Information Sciences.

[21]  Ho Gi Jung,et al.  Face occlusion detection by using B-spline active contour and skin color information , 2010, 2010 11th International Conference on Control Automation Robotics & Vision.

[22]  Rama Chellappa,et al.  Segment-Based Methods for Facial Attribute Detection from Partial Faces , 2018, IEEE Transactions on Affective Computing.

[23]  Aleix M. Martínez,et al.  A weighted probabilistic approach to face recognition from multiple images and video sequences , 2006, Image Vis. Comput..

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

[25]  Jeng-Shyang Pan,et al.  Novel Systolization of Subquadratic Space Complexity Multipliers Based on Toeplitz Matrix–Vector Product Approach , 2019, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.

[26]  Rahil Hosseini,et al.  A state-of-the-art survey of malware detection approaches using data mining techniques , 2018, Human-centric Computing and Information Sciences.

[27]  Dacheng Tao,et al.  Pose-invariant face recognition with homography-based normalization , 2017, Pattern Recognit..

[28]  Jie Lin,et al.  Robust face recognition with partial occlusion, illumination variation and limited training data by optimal feature selection , 2011 .

[29]  Sang Uk Lee,et al.  Occlusion invariant face recognition using selective local non-negative matrix factorization basis images , 2008, Image Vis. Comput..

[30]  Gunasekaran Manogaran,et al.  Intelligent face recognition and navigation system using neural learning for smart security in Internet of Things , 2017, Cluster Computing.

[31]  Muhammad Imran Razzak,et al.  Microscopic Blood Smear Segmentation and Classification Using Deep Contour Aware CNN and Extreme Machine Learning , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[32]  Martin D. Levine,et al.  Multi-path Region-Based Convolutional Neural Network for Accurate Detection of Unconstrained "Hard Faces" , 2017, 2017 14th Conference on Computer and Robot Vision (CRV).

[33]  Hanqing Lu,et al.  Occlusion Robust Face Recognition with Dynamic Similarity Features , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[34]  Ling Cheng,et al.  Long-Bone Fracture Detection using Artificial Neural Networks based on Contour Features of X-ray Images , 2019, ArXiv.

[35]  David Zhang,et al.  A Survey of Sparse Representation: Algorithms and Applications , 2015, IEEE Access.

[36]  Guolong Chen,et al.  Learning from context: A mutual reinforcement model for Chinese microblog opinion retrieval , 2018, Frontiers of Computer Science.

[37]  Hossein Mobahi,et al.  Face recognition with contiguous occlusion using markov random fields , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[38]  Thomas S. Huang,et al.  Image Super-Resolution Via Sparse Representation , 2010, IEEE Transactions on Image Processing.

[39]  Bob Zhang,et al.  Multiple representations and sparse representation for image classification , 2015, Pattern Recognit. Lett..

[40]  Stan Z. Li,et al.  Single-Shot Scale-Aware Network for Real-Time Face Detection , 2019, International Journal of Computer Vision.

[41]  Hao Wu,et al.  Simultaneous Face Detection and Pose Estimation Using Convolutional Neural Network Cascade , 2018, IEEE Access.

[42]  Daw-Tung Lin,et al.  Face Occlusion Detection for Automated Teller Machine Surveillance , 2006, PSIVT.

[43]  Tao Zhang,et al.  Fast and robust occluded face detection in ATM surveillance , 2017, Pattern Recognit. Lett..

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

[45]  Jian-Jiun Ding,et al.  Occluded face recognition using low-rank regression with generalized gradient direction , 2018, Pattern Recognit..

[46]  Sanja Fidler,et al.  Combining reconstructive and discriminative subspace methods for robust classification and regression by subsampling , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[47]  Hong Shen,et al.  Efficient Approximation Algorithms for the Bounded Flexible Scheduling Problem in Clouds , 2017, IEEE Transactions on Parallel and Distributed Systems.

[48]  Christoph Rasche,et al.  Rapid contour detection for image classification , 2017, IET Image Process..

[49]  Jianer Chen,et al.  Meta-metric for saliency detection evaluation metrics based on application preference , 2018, Multimedia Tools and Applications.

[50]  Qi Zhu,et al.  L0-norm sparse representation based on modified genetic algorithm for face recognition , 2015, J. Vis. Commun. Image Represent..

[51]  Peng Jin,et al.  Fast reference frame selection based on content similarity for low complexity HEVC encoder , 2016, J. Vis. Commun. Image Represent..

[52]  Jongsun Kim,et al.  Effective representation using ICA for face recognition robust to local distortion and partial occlusion , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[53]  Hai Su,et al.  Recent Advances in the Applications of Convolutional Neural Networks to Medical Image Contour Detection , 2017, ArXiv.

[54]  Sang Min Yoon,et al.  A New Video Surveillance System Employing Occluded Face Detection , 2005, IEA/AIE.

[55]  Cheng Lu,et al.  On the removal of shadows from images , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[56]  Jar-Ferr Yang,et al.  Robust Face Recognition under Different Facial Expressions, Illumination Variations and Partial Occlusions , 2011, MMM.

[57]  Mohit Sharma,et al.  An efficient partial occluded face recognition system , 2013, Neurocomputing.

[58]  Xianghan Zheng,et al.  Lightweight distributed secure data management system for health internet of things , 2017, J. Netw. Comput. Appl..

[59]  Yan Liu,et al.  An adaptive hybrid memetic algorithm for thermal-aware non-slicing VLSI floorplanning , 2017, Integr..

[60]  Geng Lin,et al.  Speeding up a memetic algorithm for the max-bisection problem , 2015 .