Image Morphing Using Deformation Techniques

Abstract

This paper presents a new image morphing method using a two‐dimensional deformation technique which provides an intuitive model for a warp. The deformation technique derives aC1‐continuous and one‐to‐one warp from a set of point pairs overlaid on two images. The resulting in‐between image precisely reflects the correspondence of features specified by an animator. We also control the transition behaviour in a metamorphosis sequence by taking another deformable surface model, which is simpler and thus more efficient than the deformation technique for a warp. The proposed method separates transition control from feature interpolation and is easier to use than the previous techniques. The multigrid relaxation method is employed to solve a linear system in deriving a warp or transition rates. This method makes our image morphing technique fast enough for an interactive environment.

A Survey of Morphing Techniques

“…Feature specification can be achieved by various techniques like, Mesh based warping [31], feature based constraints [4], energy minimization [17] and radial basis function [1]. Feature can also be specified using line segments, curves, points and snakes [32].…”

“…But all the methods described above do not satisfy such property. An energy minimization method has been proposed for generating one to one warp function in [17]. This technique gets warping function simulating square rubber membrane.…”

“…A new warp generation method was presented in [15] that is much simpler and faster than the related energy minimization method in [17]. Large performance gains are achieved by applying multilevel free-form deformation (MFFD) across a hierarchy of control lattices to generate one-to-one and C 2 -continuous warp function.…”

Tweening grammars: Deformation rules for representing change between discrete geographic entities

“…Their approach and concerns are for more realistic tweens, but they have not focused on tweens directly related to geospatial processes. Pasko et al 1999;Gotsman and Surazhsky 2001;Surazhsky et al 2001;Winnemöller and Bangay 2001;Pasko et al 2002;Van den Bergh et al 2002;Glassner 2003;Che et al 2004) Deformation methods (Skeleton, TIN) (Kirkpatrick and Radke 1985) Images (General) (Lee et al 1996;Surazhsky et al 2001) Medical Imaging (Shih et al 1998;Pasko et al 1999;Treece et al 1999;Surazhsky et al 2001) Topography The second table (Table 2) shows the interdisciplinary scope of this problem and that many researchers are interested in tweening. The table categorizes the research papers into the fields of the lead authors.…”

“…Discipline of lead author of the publication. Computer Graphics, Science, Animation (Martyn;Blum 1967;Blum and Nagel 1978;Catmull 1978;Reeves 1981;Kirkpatrick and Radke 1985;DeCarlo and Metaxas 1995;Shapira and Rappoport 1995;Lee et al 1996;DeCarlo and Metaxas 1998;Gao and Sederberg 1998;Lee et al 1998;Pasko et al 1999;Johan et al 2000;Bradley and Stuart 2001;Gotsman and Surazhsky 2001;Winnemöller and Bangay 2001;Pasko et al 2002;Van den Bergh et al 2002;Glassner 2003;Torsello and Hancock 2004;Yang et al 2004) Architecture & Engineering (Stiny and Gips 1972;Bertalmio et al 1998;Shih et al 1998;Treece et al 1999;Treece et al 2001) Mathematics Che et al 2004) 3. Methods…”