請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/71242
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 傅楸善 | |
dc.contributor.author | Tsun-An Hsieh | en |
dc.contributor.author | 謝尊安 | zh_TW |
dc.date.accessioned | 2021-06-17T05:00:31Z | - |
dc.date.available | 2018-08-01 | |
dc.date.copyright | 2018-08-01 | |
dc.date.issued | 2018 | |
dc.date.submitted | 2018-07-25 | |
dc.identifier.citation | [1] J. F. Blinn. “Simulation of Wrinkled Surfaces,” Proceedings of ACM SIGGRAPH Conference on Computer Graphics, vol. 12, no. 3, pp. 286–292, 1978.
[2] Q. Cao, L. Shen, W. Xie, O. M. Parkhi, and Andrew Zisserman, “VGGFace2: A Dataset for Recognising Faces Across Pose and Age,” Proceedings of IEEE Conference on Automatic Face and Gesture Recognition, Xi’an, China, pp. 1-11, 2018. [3] F. B. Haar and R. C. Veltkamp, “Expression Modeling for Expression-Invariant Face Recognition,” International Journal of Systems and Applications in Computer Graphics, vol. 34, no. 3, pp. 231-241, 2010. [4] I. A. Kakadiaris, G. Passalis, G. Toderici, M. N. Murtuza, L. Yunliang, N. Karampatziakis, and T. Theoharis, “Three-Dimensional Face Recognition in the Presence of Facial Expressions: An Annotated Deformable Model Approach,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 29, no. 4, pp. 640-649, 2007. [5] H. E. Khiyari and H. Wechsler, “Face Recognition across Time Lapse Using Convolutional Neural Networks,” Journal of Information Security, vol. 7, no. 3, pp. 141-151, 2016. [6] D. Kim, M. Hernandez, J. Choi, and G. Medioni, “Deep 3D Face Identification,” Proceedings of IEEE International Joint Conference on Biometrics, Denver, CO, USA, pp. 133-142, 2017. [7] K. Kim, T. Baltruaitis, A. Zadeh, L.-P. Morency, and G. Medioni. “Holistically Constrained Local Model: Going beyond Frontal Poses for Facial Landmark Detection,” Proceedings of British Machine Vision Conference, York, UK, pp. 95.1-95.12, 2016. [8] A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet Classification with Deep Convolutional Neural Networks,” Proceedings of Conference on Neural Information Processing Systems, Stateline, NV, USA, pp. 1106-1114, 2012. [9] S. Liang, L. G. Shapiro, and I. Kemelmacher-Shlizerman. “Head Reconstruction from Internet Photos,” Proceedings of European Conference on Computer Vision, Amsterdam, also LNCS, vol. 9906, Springer, pp. 360-374, 2016. [10] D. G. Lowe, “Distinctive Image Features from Scale-Invariant Keypoints,” International Journal of Computer Vision, vol. 60, no. 2, pp. 91-110, 2004. [11] X. Lu and A. Jian, “Deformation Modeling for Robust 3D Face Matching,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 30, no. 8, pp. 1346-1357, 2010. [12] O. M. Parkhi, A. Vedaldi, and A. Zisserman. “Deep Face Recognition,” Proceedings of British Machine Vision Conference, Swansea, UK, pp. 1-12, 2015. [13] S. J. Pan and Q. Yang, “A Survey on Transfer Learning,” IEEE Transactions on Knowledge and Data Engineering, vol. 2, no. 10, pp. 1345-1359, 2010. [14] H. Patil, A. Kothar, K. Bhurchandi, “3-d face recognition: features, databases, algorithms and challenges,” Artificial Intelligence Review, vol. 44, no. 3, pp. 393-441, 2015. [15] P. Paysan, R. Knothe, B. Amberg, S. Romhani, and T. Vetter, “A 3D Face Model for Pose and Illumination Invariant Face Recognition,” Proceedings of IEEE International Conference on Advanced Video and Signal Based Surveillance, Genoa, Italy, pp. 296-301, 2009. [16] K. Pearson, “On Lines and Planes of Closest Fit to Systems of Points in Space,” Philosophical Magazine, vol. 2, no. 11, pp. 559-572, 1901. [17] M. Piotraschke and V. Blanz. “Automated 3D Face Reconstruction from Multiple Images Using Quality Measures,” Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, Nevada, pp. 3418-3427, 2016. [18] Savran, B. Sankur, M. T. Bilge, “Regression-based Intensity Estimation of Facial Action Units,” Image and Vision Computing, vol. 30, no. 10, pp. 774-784, 2012. [19] A. Savran, N. Alyüz, H. Dibeklioğlu, O. Çeliktutan, B. Gökberk, B. Sankur, and L. Akarun, “Bosphorus Database for 3D Face Analysis,” Biometrics and Identity Management, pp. 47-56, 2008. [20] F. Schroff, D. Kalenichenko, and J. Philbin, “FaceNet: A Unified Embedding for Face Recognition and Clustering,” Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Boston, Massachusetts, pp. 815-823, 2015. [21] K. Simonyan and A. Zisserman, “Very Deep Convolutional Networks for Large-Scale Image Recognition,” Proceedings of International Conference on Learning Representations, San Diego, CA, pp. 1-14, 2015. [22] H. Su, S. Maji, E. Kalogerakis, and E. G. Learned-Miller, “Multi-view Convolutional Neural Networks for 3D Shape Recognition,” Proceedings of International Conference on Computer Vision, Santiago, Chile, pp. 945-953, 2015. [23] T. N. Tan, “CASIA-Face V5,” http://biometrics.idealtest.org/, 2010. [24] A. Tran, T. Hassner, I. Masi, E. Paz, Y. Nirkin, and G. Medioni, “Extreme 3D Face Reconstruction: Seeing through Occlusions,” Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, Utah, pp. 1-14, 2018. [25] P. Viola and M. Jones, “Rapid Object Detection Using a Boosted Cascade of Simple Features,” Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Kauai, HI, USA, pp. I-511-518, 2001. [26] Wikipedia, “Convolutional Neural Network,” https://en.wikipedia.org/wiki/Convolutional_neural_network, 2018. [27] Wikipedia, “Cross Entropy,” https://en.wikipedia.org/wiki/Cross_entropy, 2018. [28] Wikipedia, “Depth Map,” https://en.wikipedia.org/wiki/Depth_map, 2018. [29] Wikipedia, “Receiver Operating Characteristic,” https://en.wikipedia.org/wiki/Receiver_operating_characteristic, 2018. [30] Wikipedia, “Rectifier (Neural Networks),” https://en.wikipedia.org/wiki/Rectifier_(neural_networks), 2018. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/71242 | - |
dc.description.abstract | 本論文提出一個基於卷積類神經網路(Convolutional Neural Network)的方法進行三維臉部模型生成以用於資料擴增並且實現三維臉部識別的方法。過去幾年來類神經網路在二維臉部辨識上取得重大成就,例如VGG (Visual Geometry Group) Face、Inception和ResNet (Residual Network)。這些網路有含有大量參數必須由非線性最佳化的方法來調整,因此就需要大量的訓練資料來調整。2017年開始,蘋果電腦推出iPhone X智慧型手機,其中FaceID技術把人臉識別技術由二維推向三維,三維人臉辨識成為風潮。然而要訓練三維人臉辨識並不容易,首先訓練資料非常稀少,最大的三維人臉資料集中,也只有數千張人臉的深度圖,並且只有數百個個體。對此,本論文中使用遷移學習(Transfer Learning)技術來應對這個困難,並且藉由生成三維臉部模型增加訓練資料的歧異度與數量以增強三維臉部識別效能。 | zh_TW |
dc.description.abstract | A method of data augmentation for 3D face model and using it for 3D face identification is proposed in this thesis. In the past few years, researchers have achieved significant progress on 2D face identification and verification through neural network approaches, such as VGG (Visual Geometry Group) Face, GoogleNet Inception, and ResNet (Residual Network). Since there are so many hyper parameters that need to be optimized in neural networks, large data must be provided for training. In 2017, FaceID was proposed by Apple Inc. Face identification has been scaled up from 2D to 3D. However, training a 3D face classifier is difficult. 3D face datasets nowadays are so small that even a large set of 3D face (Bosphorus 3D Face Dataset) contains only 4,666 faces of 105 identities. In order to solve the lack of data, we use transfer learning [13], and several data augmentation methods by generating face mesh from different views to make the classifier more robust and discriminative. | en |
dc.description.provenance | Made available in DSpace on 2021-06-17T05:00:31Z (GMT). No. of bitstreams: 1 ntu-107-R05944036-1.pdf: 4431813 bytes, checksum: 1bb681dba5aca1ea00b857eba09f7c8b (MD5) Previous issue date: 2018 | en |
dc.description.tableofcontents | 口試委員審定書 i
誌謝 ii 中文摘要 iii ABSTRACT iv CONTENTS v LIST OF FIGURES vii LIST OF TABLES x Chapter 1 Introduction 1 1.1 Feature Extraction 3 1.2 Data Augmentation through Synthesized Faces 4 1.3 Thesis Organization 6 Chapter 2 Related Works 7 2.1 Reconstruct Human Face with Deep Convolutional Neural Network and 3D Morphable Model 7 2.1.1 Generating Training Data 7 2.1.2 Pooled 3DMM 8 2.1.3 Learning to Regress Pooled 3DMM 9 2.2 3D Face Recognition Methods 9 2.2.1 Curvature-Based Approaches 9 2.2.2 Morphable Model-Based Approaches 10 Chapter 3 Backgrounds 13 3.1 Convolutional Neural Network 13 3.2 VGG Descriptor 15 3.3 Principal Component Analysis 19 Chapter 4 Methodology 20 4.1 Overview 20 4.2 Data Augmentation 22 4.3 Fine-Tuning 26 4.4 Identification 29 Chapter 5 Experimental Results 30 5.1 Overview 30 5.2 Datasets 31 5.2.1 VGG Face2 Dataset [2]: 31 5.2.2 CASIA-Face V5 [23]: 31 5.2.3 Bosphorus Database [18, 19] 32 5.3 Evaluation 32 5.4 Analysis on Validation Set and Bosphorus Dataset 33 5.5 Visualization Views of Convolutional Kernels 38 5.5.1 Gradient Ascending 39 5.5.2 Visualization Results 39 Chapter 6 Conclusions and Future Works 46 References 47 | |
dc.language.iso | en | |
dc.title | 使用距離感測器實作三維人臉識別與重建 | zh_TW |
dc.title | 3D Face Identification and Reconstruction with Range Sensor | en |
dc.type | Thesis | |
dc.date.schoolyear | 106-2 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 施明煌,蔡安智,沈立健 | |
dc.subject.keyword | 三維臉部辨識,三維臉部生成,卷積類神經網路,遷移學習,深度學習, | zh_TW |
dc.subject.keyword | 3D Face Identification,3D Face Generation,Convolutional Neural Networks,Transfer Learning,Deep Learning, | en |
dc.relation.page | 51 | |
dc.identifier.doi | 10.6342/NTU201801902 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2018-07-26 | |
dc.contributor.author-college | 電機資訊學院 | zh_TW |
dc.contributor.author-dept | 資訊網路與多媒體研究所 | zh_TW |
顯示於系所單位: | 資訊網路與多媒體研究所 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-107-1.pdf 目前未授權公開取用 | 4.33 MB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。