Visual Morphing Based on the Compressed Domain

Visual morphing is a class of techniques that deal with the metamorphosis of one image into another, which generates a series of smoothly continuous intermediate images between two given images. Over the past few years, a number of computable models of visual morphing have been developed. However, most of these models are based on the pixel domain. Little theoretical and computational work of visual morphing is based on the compressed domain. In this paper, two image morphing algorithms in the discrete cosine transform (DCT) domain are proposed. The first method is based on the feature-based method. Salient blocks and edge blocks as features are detected in the DCT domain first. Then feature correspondences are built manually. At last, a mapping function is constructed on two hierarchies. The second method is for the case that features are not distinct and feature correspondences can’t be built easily. A morphing method following the idea of fluid simulation is proposed. The experimental results have demonstrated the convenience, efficiency and accuracy of the proposed algorithm.

[1]  I. K. Sethi,et al.  Convolution-Based Edge Detection for Image/Video in Block DCT Domain , 1996, J. Vis. Commun. Image Represent..

[2]  Steven M. Seitz,et al.  View morphing , 1996, SIGGRAPH.

[3]  Sung Yong Shin,et al.  Image Metamorphosis with Scattered Feature Constraints , 1996, IEEE Trans. Vis. Comput. Graph..

[4]  George Wolberg,et al.  Image morphing: a survey , 1998, The Visual Computer.

[5]  Jos Stam,et al.  Stable fluids , 1999, SIGGRAPH.

[6]  Sung Yong Shin,et al.  Image Morphing Using Deformation Techniques , 1996, Comput. Animat. Virtual Worlds.

[7]  Christof Koch,et al.  Feature combination strategies for saliency-based visual attention systems , 2001, J. Electronic Imaging.

[8]  Min Meng,et al.  Sketching Image Morphing Using Moving Least Squares , 2007 .

[9]  Arie E. Kaufman,et al.  Wavelet-based volume morphing , 1994, Proceedings Visualization '94.

[10]  Jos Stam,et al.  Interacting with smoke and fire in real time , 2000, CACM.

[11]  Lei Zhu,et al.  An Image Morphing Technique Based on Optimal Mass Preserving Mapping , 2007, IEEE Transactions on Image Processing.

[12]  Thaddeus Beier,et al.  Feature-based image metamorphosis , 1992, SIGGRAPH.

[13]  George Wolberg,et al.  Digital image warping , 1990 .

[14]  Lei Zhu,et al.  Image interpolation based on optimal mass preserving mappings , 2004, 2004 2nd IEEE International Symposium on Biomedical Imaging: Nano to Macro (IEEE Cat No. 04EX821).

[15]  Lei Zhu,et al.  Image morphing based on mutual information and optimal mass transport , 2004, 2004 International Conference on Image Processing, 2004. ICIP '04..

[16]  Chao-Hung Lin,et al.  Metamorphosis of 3D polyhedral models using progressive connectivity transformations , 2005, IEEE Transactions on Visualization and Computer Graphics.

[17]  Shih-Fu Chang,et al.  Survey of compressed-domain features used in audio-visual indexing and analysis , 2003, J. Vis. Commun. Image Represent..

[18]  Qian Ma,et al.  Feature-based nonrigid image registration using a Hausdorff distance matching measure , 2007 .

[19]  Thomas W. Sederberg,et al.  Free-form deformation of solid geometric models , 1986, SIGGRAPH.

[20]  Philippe Beaudoin,et al.  Particle-based viscoelastic fluid simulation , 2005, SCA '05.