Title
USSR: A Unified Framework for Simultaneous Smoothing, Segmentation, and Registration of Multiple Images
Abstract
Image smoothing, segmentation and registration are three key processing steps in many computer vision appli- cations. In this paper, we present a novel framework for achieving all three seemingly disparate goals simultane- ously across multiple images in a unified framework via a single variational principle. The proposed method ensures that the estimated registration is unbiased and all compo- sitions of registration maps are compatible. The solution to the variational problem is achieved efficiently by solv- ing a coupled system of partial differential equations over the common domain on which the registration maps are defined. The effectiveness of the proposed framework is demonstrated on sets of real images.
Year
DOI
Venue
2007
10.1109/ICCV.2007.4408969
ICCV
Keywords
Field
DocType
computer vision,image registration,image segmentation,partial differential equations,smoothing methods,variational techniques,computer vision applications,estimated registration,image registration,image segmentation,image smoothing,partial differential equations,registration maps,single variational principle,unified variational framework
Computer vision,Pattern recognition,Computer science,Segmentation,Variational principle,Image segmentation,Smoothing,Artificial intelligence,Real image,Partial differential equation,Image registration
Conference
Volume
Issue
ISSN
2007
1
1550-5499
Citations 
PageRank 
References 
9
0.65
13
Authors
3
Name
Order
Citations
PageRank
Nicholas A. Lord1514.74
Jeffrey Ho22190101.78
B.C. Vemuri34208536.42