研究生: |
徐子仁 TZU-JEN HSU |
---|---|
論文名稱: |
基於深度學習的人臉辨識系統 Face Recognition Based on Deep Learning |
指導教授: |
洪西進
Shi-Jinn Horng |
口試委員: |
郭重顯
CHONG-XIAN GUO 李正吉 ZHENG-JI LI 吳怡樂 YI-LE WU 林韋宏 WEI-HONG LIN |
學位類別: |
碩士 Master |
系所名稱: |
電資學院 - 資訊工程系 Department of Computer Science and Information Engineering |
論文出版年: | 2018 |
畢業學年度: | 106 |
語文別: | 中文 |
論文頁數: | 36 |
中文關鍵詞: | 人臉辨識 、深度學習 |
外文關鍵詞: | face recognition, deep learning |
相關次數: | 點閱:528 下載:4 |
分享至: |
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
過去的人臉辨識技術常受環境影響使得辨識度不佳,現今使用基於深度學習的人臉辨識技術能夠克服如光影等環境造成的影響,但缺點是運算能力需求高且訓練辨識模型所需的時間太長。本論文提出一個運算能力需求相對低廉且能更快速完成訓練的方法,同時小幅的提升了辨識模型的準確度。
本論文在訓練模型時使用的損失函數是由LMCL改良而來,使得模型收斂更穩定且小幅提升了辨識模型的準確度。本論文改善了訓練方式使得模型收斂的速度提升約1.8倍,CNN模型則使用MobileNet的改良版本Mobilefacenet。
In the past, the performance of face recognition technology was not ideal because of the environmental influences. These days, the impact of environment such as light and shadow to face recognition has been overcome by the technology based on deep learning, but the disadvantages are the high computational requirement and the enormous time for training a CNN model. In this paper, a method for training models has been proposed which requires relatively low computational requirements, less training time but comes with higher accuracy.
The process of model convergence has become more stable and the model accuracy is a little raised due to the modification to the loss function-LMCL in this paper. There is a speedup about 1.8 times for model convergence because of the training method improved. The CNN model used in this paper is Mobilefacenet which is improved from MobileNet.
[1] “三星S8用戶稱虹膜辨識引發眼部不適”, https://goo.gl/W7M4Ny, 06/13/2017
[2] “一張照片加隱形眼鏡就讓三星S8虹膜辨識破功”, https://goo.gl/nytjQA, 05/24/2017
[3] “Machine Learning is Fun! Part 4: Modern Face Recognition with Deep Learning”, https://goo.gl/QFZi3M, 04/09/2017
[4] Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott E. Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, and Andrew Rabinovich, “Going deeper with convolutions,” CVPR, 2015.
[5] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun, “Deep residual learning for image recognition,” CoRR, 2015.
[6] C. Szegedy, S. Ioffe, and V. Vanhoucke, “Inception-v4, inception-resnet and the impact of residual connections on learning,” CoRR, 2016.
[7] F. Chollet, “Xception: Deep learning with depthwise separable convolutions,” arXiv preprint arXiv:1610.02357, 2016
[8] G. Huang, Z. Liu, K.Q. Weinberger, “Densely connected convolutional networks,” CoRR, 2016.
[9] Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam, “Mobilenets: efficient convolutional neural networks for mobile vision applications,” CoRR, 2017.
[10] F., Schroff, D.,Kalenichenko, J.,Philbin, “Facenet: a unified embedding for face recognition and clustering,” CPVR2015.
[11] Y. Wen, K. Zhang, Z. Li, and Y. Qiao, “A discriminative feature learning approach for deep face recognition,” ECCV, 2016.
[12] F. Wang, X. Xiang, J. Cheng, and A. L. Yuille, “Normface: L2 hypersphere embedding for face verification,” ACM, 2017.
[13] F. Wang, W. Liu, H. Liu, and J. Cheng, “Additive margin softmax for face verification,” SPL, 2018.
[14] Hao Wang, Yitong Wang, Zheng Zhou, Xing Ji, Zhifeng Li, Dihong Gong, Jingchao Zhou, Wei Liu, “CosFace: large margin cosine loss for deep face recognition,” CVPR, 2018.
[15] Deng, J., Guo, J., Zafeiriou, S., “Arcface: additive angular margin loss for deep face recognition,” Arxiv preprint, 2018.
[16] N. Dalal, B. Triggs, “Histograms of oriented gradients for human detection,” CVPR, 2005.
[17] R. Lienhart, A. Kuranov, and V. Pisarevsky, “Empirical analysis of detection cascades of boosted classifiers for rapid object detection,” DAGM, 2003.
[18] Zhang, K., Zhang, Z., Li, Z., Qiao, Y., “Joint face detection and alignment using multi-task cascaded convolutional networks,” SPL, 2016.
[19] V. Kazemi, J. Sullivan, “One millisecond face alignment with an ensemble of regression trees,” CVPR, 2014.
[20] Sheng Chen, Yang Liu, Xiang Gao, and Zhen Han, “Mobilefacenets: efficient cnns for accurate real-time face verification on mobile devices,” arXiv preprint arXiv:1804.07573, 2018.
[21] “Labeled Faces in the Wild”, http://vis-www.cs.umass.edu/lfw/
[22] Min Lin, Qiang Chen, and Shuicheng Yan, “Network in network,” Arxiv, 1312.4400, 2013.
[23] S. Ioffe and C. Szegedy, “Batch normalization: accelerating deep network training by reducing internal covariate shift,” ICML, 2015.
[24] Tuxin Wu and Kaiming He, “Group normalization,” arXiv preprint arXiv:1803.08494 [cs.CV], 2018
[25] “VGGFace dataset”, http://www.robots.ox.ac.uk/~vgg/data/vgg_face/, 2015
[26] “VGGFace2 dataset”, http://www.robots.ox.ac.uk/~vgg/data/vgg_face2/, 2018
[27] “insightface”, https://github.com/deepinsight/insightface, 2018-
[28] “Early stopping”, https://en.wikipedia.org/wiki/Early_stopping
[29] S. Moschoglou, A. Papaioannou, C. Sagonas, J. Deng, I. Kotsia, and S. Zafeiriou, “Agedb: the first manually collected in-the-wild age database,” CVPR, 2017.
[30] “MegaFace”, http://megaface.cs.washington.edu
[31] “FaceScrub”, https://github.com/faceteam/facescrub
[32] Yaniv Taigman, Ming Yang, Marc’ Aurelio Ranzato, and Lior Wolf, “Deepface: closing the gap to human-level performance in face verification,” CVPR, 2014.
[33] Omkar M Parkhi, Andrea Vedaldi, Andrew Zisserman, et al, “Deep face recognition,” BMVC, 2015
[34] Yi Sun, Xiao gang Wang, and Xiaoou Tang, “Deeply learned face representations are sparse, selective, and robust,” CVPR, 2015
[35] Weihong Deng, Binghui Chen, Yuke Fang, Jiani Hu, “Deep correlation feature learning for face verification in the wild,” SPL, 2017.
[36] X. Wu, R. He, Z. Sun, and T. Tan, “A light cnn for deep face representation with noisy labels,” arXiv preprint arXiv:1511.02683, 2015.
[37] Ping Luo, Zhenyao Zhu, Ziwei Liu, Xiaogang Wang, Xiaoou Tang, “Face model compression by distilling knowledge from neurons,” AAAI, 2016.
[38] Bichen Wu, Alvin Wan, Xiangyu Yue, Peter Jin, Sicheng Zhao, Noah Golmant, Amir Gholaminejad, Joseph Gonzalez, and Kurt Keutzer, “Shift: a zero flop, zero parameter alternative to spatial convolutions,” arXiv preprint arXiv: 1711.08141, 2017.
[39] R. Ranjan, C. D. Castillo, and R. Chellappa, “L2- constrained softmax loss for discriminative face verification,” arXiv:1703.09507, 2017.
[40] DeVries, Terrance and Taylor, Graham W., “Improved regularization of convolutional neural networks with cutout,” arXiv preprint arXiv:1708.04552, 2017.
[41] K. He, X. Zhang, S. Ren, and J. Sun, “Delving deep into rectifiers: surpassing human-level performance on imagenet classification,” ICCV, 2015