An Image Morphing Technique Based on Optimal Mass Preserving Mapping

Author

Zhu, Lei ; Yang, Yan ; Haker, Steven ; Tannenbaum, Allen

Author_Institution

Dept. of Biomed. Eng., Georgia Inst. of Technol., Atlanta, GA

Volume

16

Issue

6

fYear

2007

fDate

6/1/2007 12:00:00 AM

Firstpage

1481

Lastpage

1495

Abstract

Image morphing, or image interpolation in the time domain, deals with the metamorphosis of one image into another. In this paper, a new class of image morphing algorithms is proposed based on the theory of optimal mass transport. The L² mass moving energy functional is modified by adding an intensity penalizing term, in order to reduce the undesired double exposure effect. It is an intensity-based approach and, thus, is parameter free. The optimal warping function is computed using an iterative gradient descent approach. This proposed morphing method is also extended to doubly connected domains using a harmonic parameterization technique, along with finite-element methods

Keywords

finite element analysis; gradient methods; image colour analysis; image morphing; image resolution; image sequences; L² mass moving energy functional; color interpolation; double exposure effect; finite-element methods; harmonic parameterization technique; image metamorphosis; image morphing algorithms; image sequences; intensity interpolation; intensity penalizing term; iterative gradient descent approach; optimal mass preserving mapping; optimal mass transport theory; optimal warping function; time domain image interpolation; Biomedical computing; Biomedical engineering; Biomedical imaging; Finite element methods; Hospitals; Interpolation; Iterative methods; Motion pictures; TV; Videos; Image interpolation; Monge–Kantorovich flow; image morphing; image warping; mass preserving mapping; optimal transport; Algorithms; Computer Graphics; Image Enhancement; Image Interpretation, Computer-Assisted; Imaging, Three-Dimensional; Information Storage and Retrieval; Numerical Analysis, Computer-Assisted; Signal Processing, Computer-Assisted;

fLanguage

English

Journal_Title

Image Processing, IEEE Transactions on

Publisher

ieee

ISSN

1057-7149

Type

jour

DOI

10.1109/TIP.2007.896637

Filename

4200778