بررسی روش های تشخیص چهره مبتنی بر الگوریتم های یادگیری عمیق
محورهای موضوعی : نوآوري و خلاقيت
پژمان غلام نژاد
1
*
,
احسان شریفی
2
1 - دانشگاه علوم و فنون هوایی شهید ستاری
2 - دانشگاه هوایی شهید ستاری
کلید واژه: تشخیص چهره عمیق, الگوریتمِ HMAX, الگوریتمِ B-HMAX, روش های تشخیصِ چهره, فناوریِ تشخیصِ چهره مبتنی بر بیومتریک.,
چکیده مقاله :
امروزه با رشد فناوری اطلاعات، تشخیص چهره یک مساله چالش برانگیز در زمینه تجزیه و تحلیل تصویر و بینایی رایانه است و به همین دلیل در چند سال گذشته به خاطر کاربردهای فراوان در حوزه های مختلف مورد توجه بسیاری قرار گرفته است. روش های زیادی برای پیاده سازی این فناوری مورد استفاده قرار می گیرد، اما روش کلی بر مبنای مقایسه مشخصه های خاصی از چهره افراد با یک پایگاه داده یا مجموعه اطلاعاتی از پیش ذخیره شده ( که می تواند حاصل نمونه گیری از چهره افراد باشد) است. فناوری های مبتنی بر بیومتریک در سال‌های اخیر به عنوان امیدوارکننده ترین گزینه برای تشخیص هویت افراد، شناخته شده اند. به منظور پیاده-سازی تشخیص چهره از روش های متفاوتی استفاده می شود. در این مقاله، مروری بر برخی از روش های شناخته شده پردازش تصویر انجام می شود و مزایا و معایب طرح های ذکر شده در آن بررسی شده است. همچنین فناوری های پیاده سازی سیستم های تشخیص چهره معرفی می گردد. سپس الگوریتم های تشخیص چهره بر اساس مشخصه های بیومتریک دسته بندی و معرفی می شوند. علاوه بر این، ضمن معرفی الگوریتم های مدل سلسله مراتبی و ایکس، مدل سلسله مراتبی باینری و ایکس، به بیانِ مفهوم ساختار تشخیصِ چهره ی عمیق، پرداخته شده است و برخی از جدیدترین الگوریتم های تولید شده برای این منظور ذکر شده است. در پایان، برخی از مهم ترین موارد کاربرد سیستم های تشخیص چهره مورد بررسی قرار گرفته است. هدف از این مقاله، معرفی و بیان الگوریتم های یادگیری عمیق در تشخیص چهره و بیان چالش های موجود می باشد.
Today, with the growth of information technology, face recognition is a challenging issue in the image and vision analysis of computers, and for this reason, in many years, many attention has been considered for many applications in different domains. There are many methods for implementing this technology, but the general method based on the comparison of certain characteristics of the faces of individuals with a database or pre-stored information set (which can be sampled from the sampling Be the faces of people). Biometric-based technologies have been recognized in recent years as the most promising option for identifying individuals. Different methods are used in order to implement facial diagnosis. In this paper, a review of some of the well-known image processing methods is performed and the advantages and disadvantages of the designs listed in it have been investigated. Also, the implementation of facial diagnostic systems is introduced. Then, face diagnostic algorithms are categorized and introduced based on biometric characteristics. In addition, while introducing hierarchical and X model algorithms, binary and x hierarchical model, the concept of deep face recognition structure has been addressed and some of the latest algorithms produced for this purpose. In the end, some of the most important applications of facial diagnostic systems have been studied. The purpose of this article is to introduce and express deep learning algorithms in face recognition and expression of existing challenges.
[1] S. V. Khedaskar, M. A. Rokade, B. R. Patil, and P. Tatwadarshi, "A survey of image processing and identification techniques," VIVA-Tech International Journal for Research and Innovation, vol. 1, no. 1, pp. 1-10, 2018.
[2] P. Pradhan, "Development Of Face Recognition System Using Verilook Software Development Kit," 2008.
[3] T. Kurita, "Principal component analysis (PCA)," Computer Vision: A Reference Guide, pp. 1-4, 2019.
[4] K. Sudhakar and P. Nithyanandam, "An accurate facial component detection using gabor filter," Bulletin of Electrical Engineering and Informatics, vol. 6, no. 3, pp. 287-294, 2017.
[5] P. R. G. Kurka and A. A. D. Salazar, "Applications of image processing in robotics and instrumentation," Mechanical Systems and Signal Processing, vol. 124, pp. 142-169, 2019.
[6] J. Hernandez-Ortega, J. Galbally, J. Fierrez, and L. Beslay, "Biometric quality: Review and application to face recognition with faceqnet," arXiv preprint arXiv:2006.03298, 2020.
[7] M. Krišto and M. Ivasic-Kos, "An overview of thermal face recognition methods," in 2018 41st International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO), 2018, pp. 1098-1103: IEEE.
[8] M. M. Oghaz, M. A. Maarof, M. F. Rohani, A. Zainal, and S. Z. M. Shaid, "An optimized skin texture model using gray-level co-occurrence matrix," Neural Computing and Applications, vol. 31, no. 6, pp. 1835-1853, 2019.
[9] Z. Cheng, X. Zhu, and S. Gong, "Face re-identification challenge: Are face recognition models good enough?," Pattern Recognition, vol. 107, p. 107422, 2020.
[10] Z. Cheng, X. Zhu, and S. Gong, "Surveillance face recognition challenge," arXiv preprint arXiv:1804.09691, 2018.
[11] C. Liu and F. Sun, "HMAX model: A survey," in 2015 International Joint Conference on Neural Networks (IJCNN), 2015, pp. 1-7: IEEE.
[12] M. Nazarkevych, I. Klyujnyk, I. Maslanych, B. Havrysh, and H. Nazarkevych, "Image filtration using the Ateb-Gabor filter in the biometric security systems," in 2018 XIV-th International Conference on Perspective Technologies and Methods in MEMS Design (MEMSTECH), 2018, pp. 276-279: IEEE.
[13] I. Masi, Y. Wu, T. Hassner, and P. Natarajan, "Deep face recognition: A survey," in 2018 31st SIBGRAPI conference on graphics, patterns and images (SIBGRAPI), 2018, pp. 471-478: IEEE.
[14] I. Masi, A. T. Trần, T. Hassner, J. T. Leksut, and G. Medioni, "Do we really need to collect millions of faces for effective face recognition?," in European conference on computer vision, 2016, pp. 579-596: Springer.
[15] I. Masi, T. Hassner, A. T. Tran, and G. Medioni, "Rapid synthesis of massive face sets for improved face recognition," in 2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017), 2017, pp. 604-611: IEEE.
[16] E. Richardson, M. Sela, and R. Kimmel, "3D face reconstruction by learning from synthetic data," in 2016 fourth international conference on 3D vision (3DV), 2016, pp. 460-469: IEEE.
[17] E. Richardson, M. Sela, R. Or-El, and R. Kimmel, "Learning detailed face reconstruction from a single image," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 1259-1268.
[18] P. Dou, S. K. Shah, and I. A. Kakadiaris, "End-to-end 3D face reconstruction with deep neural networks," in proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 5908-5917.
[19] Y. Guo, J. Cai, B. Jiang, and J. Zheng, "Cnn-based real-time dense face reconstruction with inverse-rendered photo-realistic face images," IEEE transactions on pattern analysis and machine intelligence, vol. 41, no. 6, pp. 1294-1307, 2018.
[20] A. Tuan Tran, T. Hassner, I. Masi, and G. Medioni, "Regressing robust and discriminative 3D morphable models with a very deep neural network," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 5163-5172.
[21] A. Tewari et al., "Mofa: Model-based deep convolutional face autoencoder for unsupervised monocular reconstruction," in Proceedings of the IEEE International Conference on Computer Vision Workshops, 2017, pp. 1274-1283.
[22] J. Liu, Y. Deng, T. Bai, Z. Wei, and C. Huang, "Targeting ultimate accuracy: Face recognition via deep embedding," arXiv preprint arXiv:1506.07310, 2015.
[23] E. Zhou, Z. Cao, and Q. Yin, "Naive-deep face recognition: Touching the limit of LFW benchmark or not?," arXiv preprint arXiv:1501.04690, 2015.
[24] C. Ding and D. Tao, "Robust face recognition via multimodal deep face representation," IEEE Transactions on Multimedia, vol. 17, no. 11, pp. 2049-2058, 2015.
[25] Y. Sun, X. Wang, and X. Tang, "Sparsifying neural network connections for face recognition," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 4856-4864.
[26] D. Wang, C. Otto, and A. K. Jain, "Face search at scale," IEEE transactions on pattern analysis and machine intelligence, vol. 39, no. 6, pp. 1122-1136, 2016.
[27] Y. Sun, X. Wang, and X. Tang, "Deeply learned face representations are sparse, selective, and robust," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2015, pp. 2892-2900.
[28] Y. Sun, D. Liang, X. Wang, and X. Tang, "Deepid3: Face recognition with very deep neural networks," arXiv preprint arXiv:1502.00873, 2015.
[29] Z. Zhu, P. Luo, X. Wang, and X. Tang, "Multi-view perceptron: a deep model for learning face identity and view representations," Advances in Neural Information Processing Systems 27 (NIPS 2014), 2014.
[30] J. Zhao et al., "Dual-Agent GANs for Photorealistic and Identity Preserving Profile Face Synthesis," in NIPS, 2017, vol. 2, p. 3.
[31] A. Shrivastava, T. Pfister, O. Tuzel, J. Susskind, W. Wang, and R. Webb, "Learning from simulated and unsupervised images through adversarial training," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 2107-2116.
[32] M. Kan, S. Shan, H. Chang, and X. Chen, "Stacked progressive auto-encoders (spae) for face recognition across poses," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2014, pp. 1883-1890.
[33] Y. Zhang, M. Shao, E. K. Wong, and Y. Fu, "Random faces guided sparse many-to-one encoder for pose-invariant face recognition," in Proceedings of the IEEE International Conference on Computer Vision, 2013, pp. 2416-2423.
[34] J. Yang, S. Reed, M.-H. Yang, and H. Lee, "Weakly-supervised disentangling with recurrent transformations for 3d view synthesis," arXiv preprint arXiv:1601.00706, 2016.
[35] M. Xi, L. Chen, D. Polajnar, and W. Tong, "Local binary pattern network: A deep learning approach for face recognition," in 2016 IEEE international conference on Image processing (ICIP), 2016, pp. 3224-3228: IEEE.
# [36] Z. Zhu, P. Luo, X. Wang, and X. Tang, "Recover canonical-view faces in the wild with deep neural networks," arXiv preprint arXiv:1404.3543, 2014.
[37] L. Hu, M. Kan, S. Shan, X. Song, and X. Chen, "LDF-Net: Learning a displacement field network for face recognition across pose," in 2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017), 2017, pp. 9-16: IEEE.
[38] E. Zhou, Z. Cao, and J. Sun, "Gridface: Face rectification via learning local homography transformations," in Proceedings of the European conference on computer vision (ECCV), 2018, pp. 3-19.
[39] R. Huang, S. Zhang, T. Li, and R. He, "Beyond face rotation: Global and local perception gan for photorealistic and identity preserving frontal view synthesis," in Proceedings of the IEEE international conference on computer vision, 2017, pp. 2439-2448.
[40] L. Tran, X. Yin, and X. Liu, "Disentangled representation learning gan for pose-invariant face recognition," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 1415-1424.
[41] J. Deng, S. Cheng, N. Xue, Y. Zhou, and S. Zafeiriou, "Uv-gan: Adversarial facial uv map completion for pose-invariant face recognition," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 7093-7102.
[42] L.-C. Chen, G. Papandreou, I. Kokkinos, K. Murphy, and A. L. Yuille, "Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs," IEEE transactions on pattern analysis and machine intelligence, vol. 40, no. 4, pp. 834-848, 2017.
[43] X. Zhang, Z. Fang, Y. Wen, Z. Li, and Y. Qiao, "Range loss for deep face recognition with long-tailed training data," in Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 5409-5418.
[44] W. Liu, Y. Wen, Z. Yu, M. Li, B. Raj, and L. Song, "Sphereface: Deep hypersphere embedding for face recognition," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 212-220.
[45] G. Hu et al., "When face recognition meets with deep learning: an evaluation of convolutional neural networks for face recognition," in Proceedings of the IEEE international conference on computer vision workshops, 2015, pp. 142-150.
[46] Q. Huang and L. Cui, "Design and Application of Face Recognition Algorithm Based on Improved Backpropagation Neural Network," Revue d'Intelligence Artificielle, vol. 33, no. 1, pp. 25-32, 2019.