論文使用權限 Thesis access permission:校內校外均不公開 not available
開放時間 Available:
校內 Campus:永不公開 not available
校外 Off-campus:永不公開 not available
論文名稱 Title |
使用調和模型之臉形變換,以及臉形邊界之產生
Face Transformation by Harmonic Model, Generating the Face Boundary |
||
系所名稱 Department |
|||
畢業學年期 Year, semester |
語文別 Language |
||
學位類別 Degree |
頁數 Number of pages |
77 |
|
研究生 Author |
|||
指導教授 Advisor |
|||
召集委員 Convenor |
|||
口試委員 Advisory Committee |
|||
口試日期 Date of Exam |
2002-06-07 |
繳交日期 Date of Submission |
2002-06-17 |
關鍵字 Keywords |
臉形變換、臉形邊界、面像合成、調和模型 combination, face transformation |
||
統計 Statistics |
本論文已被瀏覽 5713 次,被下載 0 次 The thesis/dissertation has been browsed 5713 times, has been downloaded 0 times. |
中文摘要 |
本文提出一整套面像變換與合成的新技術,即四步法:(1)找尋臉部之內外邊界,(2)用光滑曲線描寫邊界,(3)形成調和變換,(4)用Splitting-integrating 法執行臉部影像的變換。可將臉部變形,產生不同的面部表情,更可將不同的影像圖片合成,例如可以預測夫妻未來的小孩模樣。文中亦提出新的數值常微分方法(ODE)以及數值方法,它能有效結合傳統的Spline插值與ODE數值方法。 |
Abstract |
This thesis is devoted to generating the boundary of face profile for face transformation in face combining, face resembling and face recognition. The face reformation can be carried by the geometric, harmonic model and numerical methods, such as the splitting shooting method(SSM) and the splitting integrating methods(SIM) of image transformation. However, the harmonic model needs the boundary correspondence in the Dirichlet condition. It is forbidding to depict the pixel-pixel correspondence, but is necessary to find a few important, charactistic point-point correspondences. Hence, we may seek the blending curves to establish the curve-curve correspondence. In this thesis, the formulation for the face boundary and profiles are explored by three methods: cubic spline, quadratic, spline, and the ordinary differential equation(ODE) approaches using Hermite interpolation. The latter is advantageous for handling different boundary conditions in 2D clamped, simply support conditions and given curvature. The combined algorithms using both cubic splines and the ODE methods are also developed. New mathematical algorithms of curves for given curvature on the boundary are proposed in this thesis, and the number of nonlinear equations involved in curvature conditions can be reduced to two or three only. This thesis also displays the validity of the ODE approaches for 2D curves. Graphical experiments are carried out to resembling face images of a young girl, based on the photos of her parents and her childhood. |
目次 Table of Contents |
1.Introduction 2.Curves for Face Boundary: Simple cases 3.Some Other Boundary Conditions 4.Combined and Nonlinear Blending Curves 5.Intermediate Pixel-pixel Correspondence between Two Face Boundaries 6.Splitting-Integrating Method for Harmonic Transformations 7.Numerical and Graphical Experiments |
參考文獻 References |
[1] K.E. Atkinson (1989), An Introduction to Numerical Analysis(Second Ed.), John Wiley & Sons, New York, 1989. [2] R. Brunelli and T. Poggio (1993), Face recognition: Features versus templates, IEEE Trans. Patt. Anal. Machine Intell. Vol. 15, No. 10, pp. 1042-1052, 1993. [3] R.L. Burden and J. Douglas Faires (1997), Numerical Analysis(Sixth Ed.), Brooks/Cole Publishing Company, pp. 143-164, 1997. [4] R. Chellappa, C.L. Wilson and S. Sirohey (1995), Human and machine recognition of faces: A survey, Proc. IEEE Vol. 83, No. 5, pp. 705-740, 1995. [5] T. Darrel, B. Moghaddam, and A.P. Pentland (1996), Active face tracking and pose estimation in an interactive room, In Proc. Computer Vision and Pattern Recognition, pp. 67-72, San Francisco, California, Jun. 1996. [6] E.R. Dougherty and C. R. Giardina (1987), Image Processing-Continuous to Discrete, Vol.I, Geometric, Transform, and Statistical Methods, Prentice-Hall Inc., Englewood Cliffs, NJ 07632, 1987. [7] G. Farin (1990), Curve and Surfaces for Computer Aided Geometric Design, A Practical Guide,(Sec. Ed.) Academic Press, 1990. [8] J.D. Foley, A van Dam, S.K. Feiner and J.K. Hughes (1990), Computer Graphics, Principles and Practice(2nd Ed.), Addison-Wesley, Reading, MA, 1990. [9] R.C. Gonalez and R.E. Woods (1992), Digital Image Processing, Addison Wesley Pub, 1992. [10] V. Govindaraju, S.N. Srihari, and D.B. Sher (1990), A computational model for face location, In Proc. Computer Vision and Pattern Recognition, pp. 718-721, 1990. [11] L.A. Hageman and D. M. Young (1981), Applied Iteration Method, Academic Press, Boston, 1981. [12] H.T. Huang and Z.C. Li (2002), Blending curves for blending problems by numerical differential equations, III. Separation techniques, accepted by Inter. J. Computer and Mathematics with Application. [13] S.H. Jeng, H.Y.M. Liao, C.C. Han, M.Y. Chern and Y.T. Liu (1998), Facial feature detection using geometrical face model: An efficient approach, Pattern Recognition, Vol. 31, No, 3, pp. 273-282, 1998. [14] P. Juell and R. Marsh (1996), A hierarchical neural network for human face detection, Pattern Recognition, Vol. 29, No. 5, pp. 781-787, 1996. [15] T.K. Leung, M.C. Burl, and P. Perona (1995), Finding faces in clustered scenes using random labeled graph matching, In Proc. Computer Vision and Pattern Recognition, pp. 637-644, Cambridge, Mass., Jun. 1995. [16] Z. C. Li (1990), Discrete techniques for computer transformations of digital images and patterns, Pattern Recognition[SCI], Vol. 23, No. 11, pp. 1249-1273, 1990. [17] Z. C. Li, T. D. Bui, C. Y. Suen and Y. Y. Tang (1990a), Splitting-shooting methods for nonlinear transformations of digitized patterns, IEEE Pattern Anal. Machine Intell[SCI], Vol. 12, No. 7, pp. 671-682, 1990. [18] Z. C. Li, Y. Y. Tang, T. D. Bui and C. Y. Suen (1990b), Shape Transformation models and their applications in pattern recognition, Int. J. Pattern Recognition and Artificial Intell, Vol. 4, No. 1, pp. 65-94, 1990. [19] Z. C. Li, Q. L. Gu, C. Y. Suen, and T. D. Bui (1990c), A comparative study of nonlinear shape models for digital processing and pattern recognition, IEEE, Trans. on Sys., Man and Cybernetics[SCI], Vol. 20, No. 4, pp. 858-871, 1990. [20] Q. L. Gu, C. Y. Suen. T. D. Bui and Z. C. Li (1991), Font generation and shape design of character by mathematical models, Computer Processing of Chinese and Oriental Languages, Vol. 5, pp. 347-360, 1991. [21] Z. C. Li, C. Y. Suen, T. D. Bui, T. D. Tang and Q. L. Gu (1992a), Splitting-integrating methods for nonlinear images by inverse transformations, IEEE, Trans. Pattern Anal. Machine Intell[SCI], Vol. 14, pp. 678-686, 1992. [22] Z.C. Li, C.Y. Suen, T.D. Bui and Q.L. Gu (1992b), Harmonic models of shape transformations in digital images and patterns, Computer Vision, Graphs and Image Processing[SCI], Vol. 54, pp. 198-209, 1992. [23] Z.C. Li (1994), Advanced Splitting-integrating methods with high convergence rates for restoring images and patterns, J. of Scientific Computing, Vol. 9, pp. 149-172, 1994. [24] Z.C. Li (1995), Splitting-integrating method for inverse transformation of n-dimensional digital images, Numerical Algorithms, Vol. 9, pp. 181-198, 1995. [25] Z.C. Li (1996a), Splitting-integrating method for image transformations T and T^{-1}T, Computers Math. Applies, Vol. 32, pp. 32-60, 1996. [26] Z.C. Li(1996), Analysis of discrete techniques for image transformations, Numerical Algorithms, Vol. 13, pp. 225-263, 1996. [27] Z.C. Li(1998a), New discrete techniques for 3D image transformations, Inter. J. Computers & Mathematics with Application[SCI], Vol. 36, No. 4, pp. 77-109. [28] Z. C. Li(1998b), Discrete techniques for 3-D digital images and patterns, IEEE Trans. on Sys. Man and Cybern[SCI], Vol. 28, No,6, pp. 883-894, 1998. [29] Z.C. Li and Z.D.Bai(1998), Probabilistic analysis on the splitting-shooting method for image transformations, J. Computational and Applied Mathematics[JCR], Vol. 94, No. 2, pp. 69-121, 1998. [30] Z.C. Li (1999), Advanced combinations of splitting-shooting-integrating methods for digit image transformations, Inter. J. Comp. and Appl. Math., Vol. 107, pp. 147-177, 1999. [31] Z.C. Li and Y.C. Lin (2002), Image transformation by numerical methods, Technical report, Department of Applied Mathematics, National Sun Yat-sen University, Kaohsiung, 2002. [32] Z.C. Li, T.D. Bui, Y.Y. Tang and C.Y. Suen (1989), Computer transformation of Digital Images and Patterns, World Scientific, Singapore, New Jersey, London 1989. [33] Z.C. Li and H.T. Huang (2000), Blending curves for blending problems by numerical differential equations, II. Numerical methods, Computer and Mathematics with Applications, Vol. 39, pp. 165-187, 2000. [34] Z. C. Li, C. Y. Suen, T. D. Bui, T. D. Tang and Q. L. Gu(1992a), Splitting-integrating methods for nonlinear images by inverse transformations, IEEE, Trans. Pattern Anal. Machine Intell, Vol. 14, pp. 678-686, 1992. [35] Z.C. Li, C.Y. Suen, T.D. Bui and Q.L. Gu(1992b), Harmonic models of shape transformations in digital images and patterns, Computer Vision, Graphs and Image Processing, Vol. 54, pp. 198-209, 1992. [36] B.S. Manjunath (1992), A feature based approach to face recognition, In Proc. Computer Vision and Pattern Recognition, pp. 373-378, Champaign, Illinois, Jun. 1992. [37] A. Pentland, B. Moghaddam, and T. Starner (1993), View-based and modular eigenspaces for face recognition, Technical report 245, MIT Media Lab Vismod, 1993. [38] J.F. Poliakoff, Y.K. Wong and P.D. Thomas (1999), An automated curve fairing algorithm for cubic eta-spline curves, J. CAM, Vol. 102, pp. 73-85, 1999. [39] W.K. Pratt (1991), Digital Image Processing(Sec. Ed.), John Wiley & Sons Inc., 1991. [40] D.F. Rogers and J.A. Adames (1990), Mathematical Elements for Computer Graphs(Sec. Ed.), McGraw Hill. Company, 1990. [41] M.A. Shackleton and W.J. Welsh (1991), Classification of facial features for recognition, In Proc. Computer Vision and Pattern Recognition, pp. 573-579, Lahaina, Maui, Hawaii, Jun. 1991. [42] K. Sobottka and I. Pitas (1996), Extraction of facial regions and features using color and shape information, In Proc. 13th International Conference on Pattern Recognition, pp. 421-425, Vienna, Austria, Aug. 1996. [43] B.Q. Su and D. Y. Liu (1989), Computational Geometry--Curve and Surface Modelling, Academic Press, Boston, 1989. [44] K.K. Sung and T. Poggio (1994), Example-based learning for view-based human face de-tection, In Proc. Image Understanding Workshop, pp. 843-850, Monterey, Calif., Nov. 1994. [45] M. Turk and A. Pentland (1991), Eigenfaces for recognition, Journal of Cognitive Neuro-science, Vol. 3, No. 1, pp. 71-86, 1991. [46] J.S. Vandergraft (1983), Introduction to Numerical Computations, Academic Press, Inc., pp. 136-138, 1983. [47] J.J. Weng and D.L. Swets (1999), Face recognition, Chapter 3 in Biometrics, Personal Identification in Networked Society, Ed. by A.K. Jain and R. Bolle and S. Pankanti, Kluwer Academic Publishers, 1999. [48] H. Wu, Q. Chen, and M. Yachida (1995), An application of fuzzy theory: Face detection, In Proc. International Workshop on Automatic Face and Gesture Recognition, pp. 26-28, Zurich, Switzerland, Jun. 1995. [49] H. Wu, Q. Chen, and M. Yachida (1996), Facial feature extraction and face recognition, In Proc. 13th International Conference on Pattern Recognition, pp. 484-488, Vienna, Austria, Aug. 1996. [50] G. Yang and T.S. Huang (1994), Human face detection in a complex background, Pattern Recognition, Vol. 27, No. 1, pp. 53-63, 1994. [51] L. Sirovich and M. Kirby (1987), Low-dimentional procedure for the characterization of human faces, J. Opt. Soc. Am. A, Vol. 4, No. 3, 1987. [52] C. Yao and J.G. Rohne (1999), An integral linear interpolation approach to the design of incremental line algorithms, J. CAM, Vol. 102, pp. 3-19, 1999. [53] C. Zhang and F. Cheng (1999), Constructing partametric quadratic curves, J. CAM, Vol. 102, pp. 21-36, 1999. |
電子全文 Fulltext |
本電子全文僅授權使用者為學術研究之目的,進行個人非營利性質之檢索、閱讀、列印。請遵守中華民國著作權法之相關規定,切勿任意重製、散佈、改作、轉貼、播送,以免觸法。 論文使用權限 Thesis access permission:校內校外均不公開 not available 開放時間 Available: 校內 Campus:永不公開 not available 校外 Off-campus:永不公開 not available 您的 IP(校外) 位址是 3.138.33.178 論文開放下載的時間是 校外不公開 Your IP address is 3.138.33.178 This thesis will be available to you on Indicate off-campus access is not available. |
紙本論文 Printed copies |
紙本論文的公開資訊在102學年度以後相對較為完整。如果需要查詢101學年度以前的紙本論文公開資訊,請聯繫圖資處紙本論文服務櫃台。如有不便之處敬請見諒。 開放時間 available 已公開 available |
QR Code |