請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/83769完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 張智星(Jyh-Shing Jang) | |
| dc.contributor.author | Cheng-Wei Kao | en |
| dc.contributor.author | 高晟瑋 | zh_TW |
| dc.date.accessioned | 2023-03-19T21:17:16Z | - |
| dc.date.copyright | 2022-08-10 | |
| dc.date.issued | 2022 | |
| dc.date.submitted | 2022-08-05 | |
| dc.identifier.citation | [1] Yann LeCun, L?on Bottou, Yoshua Bengio, and Patrick Haffner. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278– 2324, 1998. [2] Erik Murphy-Chutorian and Mohan Manubhai Trivedi. Head pose estimation in computer vision: A survey. IEEE transactions on pattern analysis and machine intelligence, 31(4):607–626, 2008. [3] Volker Blanz and Thomas Vetter. A morphable model for the synthesis of 3d faces. In Proceedings of the 26th annual conference on Computer graphics and interactive techniques, pages 187–194, 1999. [4] Xiangyu Zhu, Zhen Lei, Xiaoming Liu, Hailin Shi, and Stan Z Li. Face alignment across large poses: A 3d solution. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 146–155, 2016. [5] Nataniel Ruiz, Eunji Chong, and James M Rehg. Fine-grained head pose estimation without keypoints. In Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pages 2074–2083, 2018. [6] Xiaojie Guo, Siyuan Li, Jinke Yu, Jiawan Zhang, Jiayi Ma, Lin Ma, Wei Liu, and Haibin Ling. Pfld: A practical facial landmark detector. arXiv preprint arXiv:1902.10859, 2019. [7] Xuanyi Dong, Yan Yan, Wanli Ouyang, and Yi Yang. Style aggregated network for facial landmark detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 379–388, 2018. [8] Rajeev Ranjan, Vishal M Patel, and Rama Chellappa. Hyperface: A deep multi-task learning framework for face detection, landmark localization, pose estimation, and gender recognition. IEEE transactions on pattern analysis and machine intelligence, 41(1):121–135, 2017. [9] Christos Sagonas, Georgios Tzimiropoulos, Stefanos Zafeiriou, and Maja Pantic. 300 faces in-the-wild challenge: The first facial landmark localization challenge. In Proceedings of the IEEE international conference on computer vision workshops, pages 397–403, 2013. [10] Cho-Ying Wu, Qiangeng Xu, and Ulrich Neumann. Synergy between 3dmm and 3d landmarks for accurate 3d facial geometry. In 2021 International Conference on 3D Vision (3DV), pages 453–463. IEEE, 2021. [11] Haibo Jin, Shengcai Liao, and Ling Shao. Pixel-in-pixel net: Towards efficient facial landmark detection in the wild. International Journal of Computer Vision, 129(12):3174–3194, 2021. [12] Priyanka Mukhopadhyay and Bidyut B Chaudhuri. A survey of hough transform. Pattern Recognition, 48(3):993–1010, 2015. [13] Mingxing Tan and Quoc Le. Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning, pages 6105–6114. PMLR, 2019. [14] Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, 25, 2012. [15] Andrea F Abate, Carmen Bisogni, Aniello Castiglione, and Michele Nappi. Head pose estimation: An extensive survey on recent techniques and applications. Pattern Recognition, 127:108591, 2022. [16] Daniel F DeMenthon and Larry S Davis. Model-based object pose in 25 lines of code. International journal of computer vision, 15(1):123–141, 1995. [17] Roberto Valle, Jos? M Buenaposada, and Luis Baumela. Multi-task head pose estimation in-the-wild. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(8):2874–2881, 2020. [18] Yi Sun, Xiaogang Wang, and Xiaoou Tang. Deep convolutional network cascade for facial point detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 3476–3483, 2013. [19] Zhen-Hua Feng, Josef Kittler, Muhammad Awais, Patrik Huber, and Xiao-Jun Wu. Wing loss for robust facial landmark localisation with convolutional neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2235–2245, 2018. [20] Alejandro Newell, Kaiyu Yang, and Jia Deng. Stacked hourglass networks for human pose estimation. In European conference on computer vision, pages 483–499. Springer, 2016. [21] Wayne Wu, Chen Qian, Shuo Yang, Quan Wang, Yici Cai, and Qiang Zhou. Look at boundary: A boundary-aware face alignment algorithm. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2129–2138, 2018. [22] Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei. Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition, pages 248–255. Ieee, 2009. [23] Karen Simonyan and Andrew Zisserman. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014. [24] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/83769 | - |
| dc.description.abstract | 現今主要的應用都是透過相機捕捉人臉的圖像，再對該圖像進行偵測、辨識或利用類似擴增實境的方式對影像進行加工，鮮少能將影像的資訊再對應回真實世界。本論文把已發展出的人臉技術作為基礎，設計一套完整的流程架構，讓使用者可以透過單目攝像機拍攝的影像預測人臉頭部寬度的實際距離，並用得到的資訊作為線上眼鏡挑選的基礎。 我們透過頭部姿勢估計與人臉特徵點檢測得到人臉與五官的位置，根據特徵選擇演算法降低特徵維度，最後透過迴歸模型預測出頭寬，此外，我們搜集了一個包含多部自拍影片的資料集，並以此為基準來衡量距離換算的誤差，衡量該方法作為實際應用的可行性。 | zh_TW |
| dc.description.abstract | Nowadays, the main application is to capture the image of the human face through a camera and implement detection, recognition or use augmented reality of adding virtual objects to the image. However, most of them cannot be mapped back to reality. In this paper, we design a complete architecture that allows users to predict the real distance of human head width through a monocular camera based on state-of-the-art facial techniques. And use the information as a criterion for online eyeglasses purchasing. We obtain the position of facial landmarks through head pose estimation and facial landmark detection, reduce the feature dimension according to the feature selection algorithm, and finally predict the head width through the regression model. Besides, we collect a dataset that contains multiple selfie videos and use it as a benchmark to measure distance conversion and measure the feasibility of real applications of our methods. | en |
| dc.description.provenance | Made available in DSpace on 2023-03-19T21:17:16Z (GMT). No. of bitstreams: 1 U0001-2707202200295900.pdf: 10354455 bytes, checksum: 721b8311f3c67ae835d4f856892aaed0 (MD5) Previous issue date: 2022 | en |
| dc.description.tableofcontents | 致謝i 摘要iii Abstract v 目錄vii 圖目錄xi 表目錄xii 第一章緒論1 1.1 研究簡介與動機. . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 1.2 研究貢獻. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 1.3 章節概述. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 第二章文獻探討3 2.1 影像深度學習模型背景知識. . . . . . . . . . . . . . . . . . . . . . 3 2.1.1 卷積神經網路. . . . . . . . . . . . . . . . . . . . . . . . . . . . 3 2.1.1.1 卷積層. . . . . . . . . . . . . . . . . . . . . . . . . . 3 2.1.1.2 池化層. . . . . . . . . . . . . . . . . . . . . . . . . . 4 2.1.1.3 全連接層. . . . . . . . . . . . . . . . . . . . . . . . 4 2.1.2 激活函數. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4 2.1.3 資料增強. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4 2.2 頭部姿勢估計. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5 2.2.1 基於臉部特徵點的頭部姿勢估計. . . . . . . . . . . . . . . . . . 6 2.2.1.1 2D 特徵點估計. . . . . . . . . . . . . . . . . . . . . 6 2.2.1.2 3D 建模. . . . . . . . . . . . . . . . . . . . . . . . . 6 2.2.2 非基於臉部特徵點的頭部姿勢估計. . . . . . . . . . . . . . . . 7 2.3 人臉特徵點檢測. . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8 2.3.1 2D 特徵點檢測. . . . . . . . . . . . . . . . . . . . . . . . . . . . 9 2.4 混合方法（hybrid methods） . . . . . . . . . . . . . . . . . . . . . . 10 第三章資料集簡介13 3.1 人臉特徵點資料集. . . . . . . . . . . . . . . . . . . . . . . . . . . . 13 3.2 MIR 頭部寬度預測資料集. . . . . . . . . . . . . . . . . . . . . . . . 14 第四章研究方法17 4.1 深度學習模型. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17 4.1.1 頭部姿勢估計模型. . . . . . . . . . . . . . . . . . . . . . . . . . 17 4.1.2 人臉特徵點檢測模型. . . . . . . . . . . . . . . . . . . . . . . . 18 4.2 整體架構. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20 4.2.1 信用卡定位. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21 4.2.1.1 Canny 邊緣檢測. . . . . . . . . . . . . . . . . . . . . 22 4.2.1.2 膨脹. . . . . . . . . . . . . . . . . . . . . . . . . . . 24 4.2.1.3 霍夫變換直線偵測. . . . . . . . . . . . . . . . . . . 25 4.2.2 迴歸. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25 4.2.2.1 線性迴歸. . . . . . . . . . . . . . . . . . . . . . . . 25 4.2.2.2 Lasso 迴歸. . . . . . . . . . . . . . . . . . . . . . . . 26 4.2.2.3 嶺迴歸. . . . . . . . . . . . . . . . . . . . . . . . . . 26 第五章實驗結果29 5.1 實驗一：臉部特徵點骨架模型. . . . . . . . . . . . . . . . . . . . . 29 5.2 實驗二：信用卡定位. . . . . . . . . . . . . . . . . . . . . . . . . . 33 5.3 實驗三：透過迴歸模型預測頭寬. . . . . . . . . . . . . . . . . . . . 37 5.3.1 特徵選擇. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 37 5.3.1.1 Sequential forward selection . . . . . . . . . . . . . . 37 5.3.1.2 主觀特徵選擇. . . . . . . . . . . . . . . . . . . . . . 41 5.3.2 基準點選擇. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 43 5.3.3 多幀預測. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 44 5.3.4 錯誤分析. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 45 第六章結論與未來展望49 6.1 結論. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 49 6.2 未來展望. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 49 參考文獻51 | |
| dc.language.iso | zh-TW | |
| dc.subject | 電腦視覺 | zh_TW |
| dc.subject | 頭部姿勢估計 | zh_TW |
| dc.subject | 深度學習 | zh_TW |
| dc.subject | 人臉特徵點檢測 | zh_TW |
| dc.subject | Facial landmark detection | en |
| dc.subject | Head pose estimation | en |
| dc.subject | Computer vision | en |
| dc.subject | Deep learning | en |
| dc.title | 使用人臉特徵點檢測與頭部姿勢估計的頭寬預測 | zh_TW |
| dc.title | Head Width Prediction Using Facial Landmark Detection and Head Pose Estimation | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 110-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 傅楸善(Chiou-Shann Fuh),葉梅珍(Mei-Chen Yeh) | |
| dc.subject.keyword | 人臉特徵點檢測,頭部姿勢估計,深度學習,電腦視覺, | zh_TW |
| dc.subject.keyword | Facial landmark detection,Head pose estimation,Computer vision,Deep learning, | en |
| dc.relation.page | 53 | |
| dc.identifier.doi | 10.6342/NTU202201754 | |
| dc.rights.note | 未授權 | |
| dc.date.accepted | 2022-08-05 | |
| 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 | |
|---|---|---|---|
| U0001-2707202200295900.pdf 未授權公開取用 | 10.11 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。