簡易檢索 / 詳目顯示

研究生: 李忠謙
Chung-chian Lee
論文名稱: 基於鼻子與眼睛幾何特徵之三維人臉檢索研究
3D human face retrieval based on nose and eyes geometry
指導教授: 邱士軒
Shih-Hsuan Chiu
口試委員: 范欽雄
Chin-Shyurng Fahn
溫哲彥
Che-yen Wen
學位類別: 碩士
Master
系所名稱: 工程學院 - 自動化及控制研究所
Graduate Institute of Automation and Control
論文出版年: 2011
畢業學年度: 99
語文別: 英文
論文頁數: 71
中文關鍵詞: 三維人臉檢索三維人臉角度校正切片輪廓簽名三維體積計算餘弦相似度
外文關鍵詞: 3D human face retrieval, 3D face normalization, Slice contour signature, 3D volume calculation, cosine similarity
相關次數: 點閱:132下載:2
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
  • 本篇文章主要提出一種全自動三維人臉檢索方法。這裡將介紹一些新的方法來提高人臉檢索的強健性與效能。總共包含了: (1) 基於眼睛偵測的三維人臉角度校正; (2) 三維人臉的臉部特徵萃取(1.雙眼與鼻尖相對位置的夾角; 2.鼻子的體積; 3.鼻子的切片輪廓。)。本研究所提出的這三種特徵,可以代表每個人鼻子的形狀及大小,以及雙眼與鼻尖角度不同的特性。主要都是利用三維才有的深度以及曲率等特徵。最後,為了針對這些特徵進行檢索,將利用餘弦相似度去計算全部人臉模型的相似度。本實驗共用33名受測者,每名受測者建6個3D模型,而我們會利用查準率與查全率去探討這些特徵的性能表現。在我們設定取出相似度最高的前六筆資料進行檢索時,我們的查準率為70%,查全率也為70%。我們可以說本研究中所採用的三個特徵能夠有效的表示人臉特徵並進行檢索。


    An automatic 3D face retrieval algorithm is presented. Several novelties are introduced to make the identification rate robust and efficient. These novelties include: (1) 3D face normalization based on eyes detection; (2) 3D facial features extraction (1.The angles between eyes and nose tip; 2.The nose volume; 3.Nose slices contour signature.). The approach works based on depth difference and curvature data. To retrieve the faces, we use the cosine similarity to calculate the similarity between all faces, and this system uses the two metrics (precision and recall) to determine the performance of the three features. In the experimental, the database is constituted by 33 subjects, and each subject has 6 3D face models. We can see that the precision rate is approaching around 70% while the top selection is set six; moreover, the recall rate is approaching around 70% in the same top selection. We can say that the three features are valid for feature representation and retrieval task.

    摘要 ABSTRACT 誌謝 CONTENTS FIGURES INDEX TABLES INDEX Chapter 1. INTRODUCTION Chapter 2. Construction of a 3D subject 2.1 The representation of 2.5D/3D images 2.2 Subject Reconstruction in Object Files (.obj) Chapter 3. EXPERIMENTAL EQUIPMENT 3.1 Introduce the Structure-light 3D scanner 3.2 The 3D scanner in this research Chapter 4. RESEARCH METHODOLOGY 4.1 Preprocess 4.1.1 Face denoising 4.1.2 Eyes detection and location 4.1.3 Face normalization based on eyes detection 4.2 3D feature extraction 4.2.1 Eyes and nose angle calculation 4.2.2 Nose slices contour signature 4.2.3 Nose volume calculation 4.3 Cosine similarity Chapter 5. EXPERIMENTAL RESULT AND DISCUSSION 5.1 The result of preprocess and 3D feature extraction 5.1.1 The result of preprocess 5.1.2 The result of 3D feature extraction 5.2 The result of 3D face retrieval Chapter 6. CONCLUSION AND FUTURE WORK 6.1 Conclusion 6.2 Future work REFERENCE

    [1] 許立佑, 「三維人臉模型化與手勢辨識」, 國立清華大學電機工程學系碩士論文, 民國98年7月。
    [2] Wang, Y. and Liu, J. and Tang, X. "Robust 3D face recognition by local shape difference boosting," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 32, no. 10, pp. 1858–1870, 2010.
    [3] Scheenstra, A. and Ruifrok, A. and Veltkamp, R.C. “A Survey of 3D Face Recognition Methods,” Proc. Int’l Conf. Audio- and Video-Based Biometric Person Authentication, pp. 891-899, 2005.
    [4] Bowyer, K.W. and Chang, K. and Flynn, P. “A Survey of Approaches and Challenges in 3D and Multi-Modal 2D+3D Face Recognition,” Computer Vision and Image Understanding, vol. 101, no. 1, pp. 1-15, 2006.
    [5] Abate, A.F. and Nappi, M. and Riccio, D. and Sabatino, G. "2D and 3D face recognition: A survey", presented at Pattern Recognition Letters, 2007, pp.1885-1906.
    [6] Blanz, V., Vetter, T., "Face Recognition Based on Fitting a 3D Morphable Model", presented at IEEE Trans. Pattern Anal. Mach. Intell., 2003, pp.1063-1074.
    [7] Lu, X., Hsu, R., Jain, A., Kamgar-Parsi, B., Kamgar-Parsi, B., "Face Recognition with 3D Model-Based Synthesis", in Proc. ICBA, 2004, pp.139-146.
    [8] Ansari, A., Abdel-Mottaleb, M., "3-D Face Modeling Using Two Views and a Generic Face Model with Application to 3-D Face Recognition", in Proc. AVSS, 2003, pp.37-44.
    [9] Cook, J., Chandran, V., Sridharan, S., Fookes, C., "Face Recognition from 3D Data using Iterative Closest Point Algorithm and Gaussian Mixture Models", in Proc. 3DPVT, 2004, pp.502-509.
    [10] Besl, P.J., McKay, N.D., "A Method for Registration of 3-D Shapes", presented at IEEE Trans. Pattern Anal. Mach. Intell., 1992, pp.239-256.
    [11] Moreno, A.B., Sanchez, A., Velez, J.F., Diaz, F.J. “Face recognition using 3D surface-extracted descriptors.” In: Proc. Irish Machine Vision and Image, (IMVIP’03), 2003, September.
    [12] Chang, K., Bowyer, K., Flynn, P., “Face Recognition using 2D and 3D facial data,” In: Proc. ACM Workshop on Multimodal User Authentication December, 2003, pp. 25–32.
    [13] Chang, K., Bowyer, K., Flynn, P., "An Evaluation of Multimodal 2D+3D Face Biometrics", presented at IEEE Trans. Pattern Anal. Mach. Intell., 2005, pp.619-624.
    [14] Papatheodorou, T., Rueckert, D., "Evaluation of Automatic 4D Face Recognition Using Surface and Texture Registration", in Proc. FGR, 2004, pp.321-326.
    [15] Faltemier, T.C. and Bowyer, K.W. and Flynn, P.J. "A Region Ensemble for 3-D Face Recognition", presented at IEEE Transactions on Information Forensics and Security, pp.62-73,(2008)
    [16] Mian, A.S. and Bennamoun, M. and Owens, R.A. "Keypoint Detection and Local Feature Matching for Textured 3D Face Recognition", presented at International Journal of Computer Vision, pp.1-12(2008).
    [17] Mayo, M. and Zhang, E. "3D Face Recognition Using Multiview Keypoint Matching", in Proc. AVSS, pp.290-295(2009).
    [18] Boehnen, C., Peters, T., and Flynn, P.J. "3D Signatures for Fast 3D Face Recognition", in Proc. ICB, pp.12-21(2009).
    [19] Huang, D., Ardabilian, M., Wang, Y., and Chen, L. "A novel geometric facial representation based on multi-scale extended local binary patterns", in Proc. FG, pp.1-7(2011).
    [20] Toriwaki, J. and Yoshida, H. "Fundamentals of Three-dimensional Digital Image Processing", pp.1-11(2009).
    [21] Furht, B. “Encyclopedia of Multimedia (2nd ed.),” Springer, pp.222(2008).
    [22] Wikipedia,(2008), “Structured-light 3D scanner” http://en.wikipedia.org/wiki/Structured-light_3D_scanner, 1 July 2011.
    [23] 冬陽,3D遊戲程式設計,第2-26~2-28頁,台北 宸宇出版社,民國九十二年
    [24] Hsu, R.L. and Mohamed, A.M. and Jain, A.K., "Face Detection in Color Images," IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 24, No. 5, pp.696-706(2002).
    [25] Nasiri, J. A. and Moulavi, M. A. and Nazemi, S. and Deldari, H. and Yazdi, H. S. and Eshghi, A. "An Efficient Parallel Eye Detection Algorithm on Facial Color Images", (SNPD' 08), 9th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing (2008).
    [26] Jackway, P.T. and Deriche, M., "Scale-space properties of the multiscale morphological dilation-erosion," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 18, pp. 38–51(1996).
    [27] 黃勝達,”應用二維人臉影像與三維點雲資料於人臉姿態估側之研究”,國立臺灣科技大學高分子工程系碩士學位論文,民國99年7月
    [28] 冬陽,3D遊戲程式設計,第3-16~3-20頁,台北 宸宇出版社,民國九十二年
    [29] Gonzalez, R. C. and Woods, R. E., "Digital Image Processing," 3rd Edition, Prentice Hall, New Jersey, (2008).
    [30] Hsieh, C. H. and Kuo, C. M. and Tsai, H. C. “Trademark Retrieval Using Contour Signature and Primitive Patterns,” 16th IPPR Conference on Computer Vision, Graphics, and Image Processing , R.O.C. (2003)
    [31] 黃議賜,”應用輪廓簽名特徵於鞋印圖形檢索”,國立臺灣科技大學高分子工程系碩士學位論文,民國96年7月
    [32] Schneider, P. J. and Eberly, D. H. “Geometric Tools for Computer Graphics,” Elsevier Science, USA, pp. 820-825(2003)
    [33] Tan, P. N., Steinbach, M. and Kumar, V. "Introduction to Data Mining", Addison-Wesley, chapter 8; page 500(2005)
    [34] Olson, D. L. and Delen, D. ”Advanced Data Mining Techniques” Springer; 1 edition, , p.p. 138(2008)

    QR CODE