臺灣博碩士論文加值系統

本論文提出一種三維人臉影像檢索方法。首先將三維人臉影像做前處裡，包含去雜訊以及人臉正規化，接著將取人臉之特徵，擷取之特徵有鼻子體積、雙眼與鼻尖相對位置的夾角以及鼻子的切片輪廓簽名等三種特徵以及本研究提出新的特徵，包括鼻寬、鼻高、鼻樑長度以及鼻翼與嘴角長度。為了針對這些特徵進行檢索，將利用歐式距離來計算出受測影像與資料庫影像之相似度，本實驗之資料庫包含70名受測者，每名受測者建6個3D模型，最後我們會利用平均檢索率來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，平均檢索率為81%。我們可以說本研究中所採用特徵能夠有效的表示人臉特徵並進行檢索。

The 3D face retrieval algorithm is presented. At first, to preprocess of 3D face image, include face denoising and face normalization, next to extract feature, the feature have the nose volume, the angles between eyes and nose tip, nose slices contour signature and we proposed the new features include the nose width, nose height, the length of ridge of nose and the length from nose wings to mouth corner. To retrieve the faces, we use the Euclidean distance to measure between the vectors of query image and the database image. In the experimental, the database is constituted by 70 subjects, and each subject has 6 3D face models. Finally, this system uses the average retrieval rate to determine the performance of these features. The experimental results show that the average retrieval rate is approaching around 81% while the top selection is set six. We can say that these features are valid for feature representation and retrieval task.

摘要 I
ABSTRACT II
誌謝 III
Contents IV
List of Figures VI
List of Tables VIII
Chapter 1 Introduction 1
1.1 Background 1
1.2 Literature Review 2
1.3 Objects of research 7
1.4 Structure of thesis 8
Chapter 2 Construction of a 3D subject 9
2.1 3D Modeling Principle 9
2.2 The 3D scanner in this research 10
2.3 Object File Format(.obj) 12
Chapter 3 Research Methodology 14
3.1 3D face image preprocess 15
3.1.1 Face denoising 15
3.1.2 Eyes detection and location 16
3.1.3 Face normalization 18
3.2 3D facial feature extraction 26
3.2.1 The length of ridge of nose 26
3.2.2 Nose width and nose height 28
3.2.3 The length from nose wing to mouth corner 31
3.3 Euclidean distance 34
3.4 Average retrieval rate 35
Chapter 4 Experimental Results and analysis 36
4.1 The result of preprocess and feature extraction 36
4.1.1 The result of preprocess 36
4.1.2 The result of feature extraction 39
4.2 Retrieval result and analysis 43
Chapter 5 Conclusions and Future work 49
5.1 Conclusions 49
5.2 Future Work 50
REFERENCES 51

[1]Mingquan, Z., Xiaoning, L., Guohua, G., “3D Face Recognition Based on Geometrical Measurement” In: Proceeding of Proceedings of the 5th Chinese conference on Advances in Biometric Person Authentication, China(2004).
[2]Moe Ma Ma Tin., Myint Myint Sein., “MULTI TRIANGLE BASED AUTOMATIC FACE RECOGNITION SYSTEM BY USING 3D GEOMETRIC FACE FEATURE”. In:
proceeding of International Instrumentation and Measurement Technology
Conference, Singapore, May, pp. 5-7 (2009).
[3]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.
[4]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.
[5]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.


[6]Hu, Y.X., Jiang, D.L., Yan, S.C., Zhang, H.J., 2004. Automatic 3D Reconstruction for Face Recognition. In: Proc. Proceeding of IEEE International Conf. on Automatic Face and Gesture Recognition, Seoul, Korea, May, pp. 843–850 (2004).
[7]林建良，”使用三維虛擬人臉之辨識系統”，國立成功大學工程科學系碩士學
位論文，民國97年7月
[8]Moreno, A.B., Sanchez, A., Velez, J.F., Diaz, F.J. 2003. Face recognition using 3D surface-extracted descriptors. In: Proc. Irish Machine Vision and Image, (IMVIP’03), September.
[9]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.
[10]Wang, Y., Pan, G., Wu, Z., 2004. Sphere-spin-image: A view point invariant surface representation for 3D face recognition. In: Proc.Internat. Conf. on Computational Science (ICCS’04), Lecture Notes in Computer Science, Vol. 3037 (June), pp. 427–434.
[11]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.
[12]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.
[13]Bronstein, A., Bronstein, M., Kimmel, R., 2003. Expression-invariant 3D face recognition. Proc. Audio & Video-based Biometric Person Authentication (AVBPA). In: Lecture Notes in Computer Science, Vol. 2688. Springer, pp. 62–69.
[14]T. Maurer, D. Guigonis, I. Maslov, B. Pesenti, A. Tsaregorodtsev, D. West, G. Medioni, Performance of geometrix activeidtm 3D face recognition engine on the frgc data, in: IEEE Workshop on Face Recognition Grand Challenge Experiments, June 2005.
[15]Medioni, G., Waupotitsch, R., 2003. Face recognition and modeling in 3D. In: Proc. IEEE Internat. Workshop on Analysis and Modeling of Faces and Gesture Recognition (AMFG’03). Nice, France, October,pp. 232–233.
[16]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.
[17]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.
[18]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).
[19]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).
[20]Boehnen, C., Peters, T., and Flynn, P.J. "3D Signatures for Fast 3D Face
Recognition", in Proc. ICB, pp.12-21(2009).
[21]李忠謙，”基於鼻子與眼睛幾何特徵之三維人臉檢索研究”，國立台灣科技大學自動化與控制研究所碩士學位論文，民國99年7月
[22]Furht, B. “Encyclopedia of Multimedia (2nd ed.),” Springer, pp.222(2008).
[23]Wikipedia,(2008), “Structured-light 3D scanner”
http://en.wikipedia.org/wiki/Structured-light_3D_scanner, 1 July 2011.
[24]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
[25]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).

[26]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).
[27]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).
[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]Miloš ORAVEC and Branislav KRIŠTOF and Michal KOLARIK and Jarmila PAVLOVIČOVA., "Extraction of Facial Features from Color Images", RADIOENGINEERING, vol. 17, No. 3, (2008)
[30]Euclidean distance, http://en.wikipedia.org/wiki/Euclidean_distance, 1 July 2012.
[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