By Topic

Nonlinear warping function recovery by scan-line search using dynamic programming

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

1 Author(s)
F. Porikli ; Mitsubishi Electr. Res. Lab., Cambridge, MA, USA

We present a novel solution to the warping recovery problem. Our algorithm has several distinct advantages; it is scalable, it enables effective integration of boundary and continuity constraints, and most importantly it is computationally much less demanding than the previous approaches. In addition, our algorithm accurately detects non-linear warping functions without being restricted to the linearity assumptions and 2-D planar deformations unlike the existing methods. We achieve to formulate the image warping as an optimization process in 1-D scan-line search spaces. We construct the search spaces from block-matching based image distances, and then we traverse minimum cost paths into these search spaces using boundary conditions to determine the horizontal and vertical components of warping for each pixel. Our experiments prove the performance of the proposed algorithm.

Published in:

Image Processing, 2004. ICIP '04. 2004 International Conference on  (Volume:3 )

Date of Conference:

24-27 Oct. 2004