Autocorrespondence: feature-based match estimation and image metamorphosis
- 19 November 2002
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3, 2736-2741
- https://doi.org/10.1109/icsmc.1995.538197
Abstract
This paper addresses the problem of matching distinct b ut related objects across images, for applications such as vie w-based model capture, virtual presence, and morphing special effects. A new approach to match estimation is presented for estimating cor - respondances between distinct objects. This approach minimizes the effects of lighting variations and non-rigid deformations. A sparse set of features are used for alignment, followed by image- plane warping, or morphing, based on these constraints.Keywords
This publication has 8 references indexed in Scilit:
- Face recognition from one example viewPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Non-parametric local transforms for computing visual correspondencePublished by Springer Nature ,1994
- Efficient multiscale regularization with applications to the computation of optical flowIEEE Transactions on Image Processing, 1994
- A novel video coding scheme based on temporal prediction using digital image warpingIEEE Transactions on Consumer Electronics, 1993
- Feature-based image metamorphosisPublished by Association for Computing Machinery (ACM) ,1992
- The design and use of steerable filtersPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991
- A computational framework and an algorithm for the measurement of visual motionInternational Journal of Computer Vision, 1989
- Shape Matching of Two-Dimensional ObjectsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1984