摘要
图像变形(image warping)技术是在计算机图形学和数字图像处理的基础上发展而来，它通常是通过几何形状的扭曲和颜色的插值来实现，也就是将二维几何变换应用到图像上以保留其特征之间的几何队列，同时混合它们的颜色，其主要包括交叉分解方法和基于特征的方法。我们经常在科幻电影中看到一副图像流畅地变为另一副图像，这就是交叉分解，也是图像变形技术中最简单的一种。而基于特征的方法会产生更加有趣的视觉效果，它先在两个不同的图像上选择对应的特征，建立它们之间的对应映射函数，通过变形可以让一副图像具有另一副图像的特征。例如，让一副人脸图像中眼睛具有第二副人脸图像中眼睛的特征。
图像变形技术可以被广泛地应用于：科幻电影制作，三维重建，刑事侦破，外科人脸整形手术效果预见，人脸检测以及人脸图像合成等方面。
本文首先介绍了图像变形技术的基本原理，然后详细叙述了几种比较典型的变形方法，并提出一种新的基于snake模型的图像变形技术，最后用图像参数对这几种方法进行了比较，并给出了相应的结论。
Image warping technology developed based on the computer graphics and digital image processing,it finished the work through the distortion of geometry figure and the color interpolation,i.e.,image warping applies two-dimension geometry transformation on images to retain the alignment between their features,at the same time blends their colors. It mostly includes cross-dissolve method and feature-based methods, we often see a image transform into another fluently in science films.it is the simplest warping method,however,the feature-based method will bring more interesting visual effect,firstly select the corresponding features on the different images,then establish the mapping function based on these corresponding relative, at last though warping we can make one image take on another image's feature, e.g. we can make the eye on one face image look like that of the other face image.
Image warping technology can be widely applied in: making of science film, three dimension reconstruction, criminal detection, effect forecast of surgery face plastic surgery,face detection and face image amalgamation,etc.
The dissertation described the fundamental of image warping technology firstly, then recount the several typical methods of image warping ,and bring forward a new snake-based model image warping method,at last compare these methods through making use of image parameters and present the corresponding conclusion.
引文
[1]Kenneth R. Castleman, Digital Image Processing, 2002.2
[2]Beier T, Neely S, Feature-based image metamorphosis. (Proceedings of SIGGRAPH'92) Comput Graph 26:35-42
[3]Bookstein, E L., Principal Warps: Thin Plate Splines and Decomposition Deformations, IEEE Trans.Pattern Anal .Mach. Intell. 11, June 1989
[4]Meinguet, J. Multivariate Interpolation at Arbitrary Points Made Simple, Appl. Math. Phys. 30, 292-304, 1979
[5]G.A.Micchelli. Interpolation of Scattered data:distance matrices and conditionally positive definite functions.Constructive Approximation, 2:11-22, 1986
[6]J, Duchon, Splines minimizing rotation-invariant semi-norms in Sobolev spaces, Multivariate Approximation Theory, pages 85-100, 1979
[7]P.S.Hechbert, Survey of texture mapping, IEEE Computer Graphics and application 6(11):56-67, November 1986
[8]N.Dyn and G. Wahba, On the estimation of functions of several variables from aggregated data, SIAM Journal Of Mathematical Analysis, 13(1): 134-152, 1982
[9]G. Wolberg, Digital Image Warping, IEEE Computer Society Press, 1990
[10]Smythe DB, A two-pass mesh warping algorithm for object gransformation and image interpolation, Technical report 1030, ILM Computer Graphics Department, Lucasfilm, San Rafael, Calif
[11]Lee s, Chwa K-Y, Hahn J, Shin SY(1996), Image morphing using deformation techniques, Visualization Comput Anim 7:3-23
[12]Lee S, Chwa K-Y, Shin SY, Wolberg G(1995), Image metamorphosis using snake and free-form deformations. Comput Graph, pp 439-448
[13]Sederberg TW, Parry SR(1986), Free-form deformation of solid geometric models. Comput Graph 20:151-160
[14]Brown LG(1992), A survey of image registration techniques, ACM Comput surveys 24:325-376
[15]Tekalp AM (1995), Digital video processing, Prentice Hall PTR, Upper Saddle River, NJ
[16]Gao p, Sederberg TW(1998), A work minimization approach to image morphing, Visual Comput
[17]Ruprecht D, Muller H, Deformed cross-dissovles for interpolation in scientific visualization, J Visualization Comput Anim 5:167-181
[18]Bichsel M(1996), Automatic interpolation and recognition of face images by morphing, The
2nd International on Automatic Face and Gesture Recognition, Killington, Vermont, IEEE Computer Society Press, Los Alamitos, CA, pp 128-135
[19]Covell M, Eigen-points:control-point location using principal component analysis, The 2nd International on Automatic face and gesture recognition, Killington, Vermont, IEEE Computer Society Press, pp 122-127
[20]Bregler C, Covell M, Slaney M(1997), Video rewrite:driving visual speech with audio. (Proceedings of SIGGRAPH'97), Comput Graph, pp 353-360
[21]Ezzat T, Poggio T (1996), Facial analysis and synthesis using image-based models, The 2nd International on Automatic Face and Gesture Recognition, Killington, Vermont, IEEE Computer Society Press, Los Alamitos, CA, pp 116-121
[22]M.Kass, A.Witkin and D.Terzopoulos, Snake: Active Contour Model, Int J.Computer Vision, Vol, pp.321-331, 1987
[23]R.Courant, D.Hibert, Methods of mathematical physics, Volume 1.Interscience, New York, 1953
[24]D.Williams and M.Shah, A Fast Algorithm for Active Contours and Curvature Estimation, CVGIP: Image Understanding. Vol.55, No. 1, January. 1992, pp. 14-26
[25]C.Xu, J.L.Prince, Snakes, shapes, and gradient vector flow, IEEE Trans .on Image Processing. 7(3):359-369, March 1998
[26]C.Xu, J.L.Prince. Generalized gradient vector flow external forces for active contours, Signal Processing, An International Journal, 71 (2): 132-139, 1998
[27]C.Xu, J.L.prince, Gradient Vector Flow Deforable Models, Handbook of Medical Imaging, 2000
[28]B.K.P.Horn, B.G. Schunck, Determining optical flow, Artificial Intelligence, 17:185-203, 1981
[29]夏德深，傅德胜，现代图像处理技术与应用，东南大学出版社 1997
[30]殷德奎，俞卞章，佟明安，基于多维直方图的灰度图像质量评价，模式识别与人工智能，1996
[31]张兵等，中巴地球资源一号卫星数据质量评价与地质应用，中巴地球资源卫星数据应用评价文集，2000
[32]曾生根，仲海泉等，从图像工程角度看CBERS-1卫星图像，航天返回与遥感，2001 Vol．22 No．3
[33]Volker Blanz, Thomas Vetter, A Morphable Model For The Synthesis Of 3D Faces
[34]Volker Blanz, Thomas Vetter, Face Recognition Based on Fitting a 3D Morphable Medel
[35]Alireza Bab-Hadiashar, David Suter and Ray Jarvis, Optic Flow Computation Using Interpolating Thin-Plate Splines
[36]Andres Bruhn, Joachim Weickert, Christian Feddem, Timo Kohlberger and Christoph
Schnorr, Real-Time Optic Flow Computation with Variational Methods
[37]D.Terzopoulos, J.Platt, A.Barr, and K.Fleischer. Elastically deformable models, Computer Graphics, 21(4):205-214, 1987
[38]Bookstein FL(1991) Morphometric tools for landmark data. Cambridge University Press, New York
[39]D.Norvila and J.Dixon, Computer-generated Metamorphoses Evolve, IEEE Spectrum, April, 1992
[40]J.R.Bergen and R.Hingorani, Hierarchical motion-based frame rate conversion. Technical report, David Sarnoff Research Center Princeton NJ 08540,1990
[41]D.Beymer and T. Poggio, Image representation for visual learning, Science. 272:1905-1909, 1996
[42]D.Beymer, A.SHashua, and T.Poggio, Example-based image analysis and synthesis. A.I.Memo No 1431. Artificial Intelligence Laboratory, Massachusetts Institute of Technology, 1993
[43]C.S.Choi, T. Okazaki, H.Harashima, and T.Takebe, A system of analyzing and synthesizing facial images. In Proc. IEEE Int. Symposium of Circuit and Syatems(ISCAS91), pages2665-2668,1991
[44]A.Lanitis, C.J.Taylor, and T.F.Cootes. Automatic interpretation and coding of face images using flexible models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 19(7):743-756, 1997
[45]F.Pighin, J.Hecker, D.Lischinske, Szeliski R, and D.Salesin, Synthesizing realistic facial expressings from photographs. In Computer Graphics Proceedings SIGGRAPH'98, pages 75-84, 1998
[46]L.Sirovich and M.Kirby. Low-dimensional procedure for the characterization of human faces.Journal of the Optical Society of America A, 4:519-554, 1987
[47]T.Vetter and T.Poggio, Linear object classes and image synthesis from a single example image. IEEE Transactions on Pattern Analysis and Machine Intelligence, 19(7):733-742, 1997