A Multi-Scale Parallel Convolutional Neural Network Based Intelligent Human Identification Using Face Information
2
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
Intelligent human identification using face information has been the research hotspot ranging from Internetof Things (IoT) application, intelligent self-service bank, intelligent surveillance to public safety and intelligentaccess control. Since 2D face images are usually captured from a long distance in an unconstrained environment,to fully exploit this advantage and make human recognition appropriate for wider intelligent applicationswith higher security and convenience, the key difficulties here include gray scale change caused byillumination variance, occlusion caused by glasses, hair or scarf, self-occlusion and deformation caused bypose or expression variation. To conquer these, many solutions have been proposed. However, most of themonly improve recognition performance under one influence factor, which still cannot meet the real facerecognition scenario. In this paper we propose a multi-scale parallel convolutional neural network architectureto extract deep robust facial features with high discriminative ability. Abundant experiments are conductedon CMU-PIE, extended FERET and AR database. And the experiment results show that the proposedalgorithm exhibits excellent discriminative ability compared with other existing algorithms.
Abstract
Intelligent human identification using face information has been the research hotspot ranging from Internetof Things (IoT) application, intelligent self-service bank, intelligent surveillance to public safety and intelligentaccess control. Since 2D face images are usually captured from a long distance in an unconstrained environment,to fully exploit this advantage and make human recognition appropriate for wider intelligent applicationswith higher security and convenience, the key difficulties here include gray scale change caused byillumination variance, occlusion caused by glasses, hair or scarf, self-occlusion and deformation caused bypose or expression variation. To conquer these, many solutions have been proposed. However, most of themonly improve recognition performance under one influence factor, which still cannot meet the real facerecognition scenario. In this paper we propose a multi-scale parallel convolutional neural network architectureto extract deep robust facial features with high discriminative ability. Abundant experiments are conductedon CMU-PIE, extended FERET and AR database. And the experiment results show that the proposedalgorithm exhibits excellent discriminative ability compared with other existing algorithms.
참고문헌 (26)
- W. Song, "A real-time infrared LED detection method for input signal positioning of interactive media", Journal of Convergence, 7 (2016)
- P. J. Phillips, "FRVT 2006 and ICE 2006 large-scale experimental results", IEEE Transactions on Pattern Analysis and Machine Intelligence, 32(5), pp.831~846 (2010)
- Report on the evaluation of 2D still-image face recognition algorithms, "P. J. Grother", National Institute of Standards and Technology, ~, pp.NIST Interagency Report No. 7709 (2010)
- A. Moeini, "Unconstrained pose-invariant face recognition by a triplet collaborative dictionary matrix", Pattern Recognition Letters, 68, pp.83~89 (2015)
- K. Ramirez-Gutierrez, "A face recognition algorithm using eigenphases and histogram equalization", International Journal of Computers, 5(1), pp.34~41 (2011)
- Sajid Ullah Khan, "X-Ray Image Enhancement Using a Boundary Division Wiener Filter and Wavelet-Based Image Fusion Approach", JIPS(Journal of Information Processing Systems), 12(1), pp.35~45 (2016), 한국정보처리학회[DOI]
- Z. Nenadic, "Information discriminant analysis : Feature extraction with an information-theoretic objective", IEEE Transactions on Pattern Analysis and Machine Intelligence, 29(8), pp.1394~1407 (2007)
- L. Lei, "Face recognition using LBP eigenfaces", IEICE Transactions on Information and Systems, 97(7), pp.1930~1932 (2014)
- J. Li, "The combination of CSLBP and LBP feature for pedestrian detection", Proceedings of 2013 3rd International Conference on Computer Science and Network Technology (ICCSNT), pp.543~546 (2013)
- A. R. Rivera, "Local directional number pattern for face analysis : face and expression recognition", IEEE Transactions on Image Processing, 22(5), pp.1740~1752 (2013)
- A. R. Rivera, "Spatiotemporal directional number transitional graph for dynamic texture recognition", IEEE Transactions on Pattern Analysis and Machine Intelligence, 37(10), pp.2146~2152 (2015)
- J. Ylioinas, "Computer Vision-ACCV 2012", pp.375~388 (2012), Springer
- C. Shan, "Facial expression recognition based on local binary patterns : a comprehensive study", Image and Vision Computing, 27(6), pp.803~816 (2009)
- X. Z. Liu, "Dual-kernel based 2D linear discriminant analysis for face recognition", Journal of Ambient Intelligence and Humanized Computing, 6(5), pp.557~562 (2015)
- X. Z. Liu, "Kernel-based 2D fisher discriminant analysis with parameter optimization for face recognition", International Journal of Pattern Recognition and Artificial Intelligence, 27(8) (2013)
- B. Zhang, "Robust classification for occluded ear via Gabor scale feature-based non-negative sparse representation", Optical Engineering, 53(6) (2013)
- L. Yuan, "Non-negative dictionary based sparse representation classification for ear recognition with occlusion", Neurocomputing, 171, pp.540~550 (2016)
- D. Ciresan, "Multi-column deep neural networks for image classification", Proceedings of 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp.3642~3649 (2012)
- P. Sermanet, "Pedestrian detection with unsupervised multistage feature learning", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.3626~3633 (2013)
- T. Wang, "End-to-end text recognition with convolutional neural networks", Proceedings of 2012 21st International Conference on Pattern Recognition (ICPR), pp.3304~3308 (2012)
- P. Luo, "Hierarchical face parsing via deep learning", Proceedings of 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp.2480~2487 (2012)
- Y. Taigman, "DeepFace: closing the gap to human-level performance in face verification", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.1701~1708 (2014)
- O. M. Parkhi, "Deep face recognition", Proceedings of the British Machine Vision Conference (BMVC) (2015)
- "DeepID3: face recognition with very deep neural networks" (2015)[URL]
- F. Schroff, "FaceNet: a unified embedding for face recognition and clustering", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.815~823 (2015)
- C. Szegedy, "Going deeper with convolutions", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.1~9 (2015)