A framework for efficient correspondence using feature interrelations

We propose a formulation for solving the point pattern correspondence problem, relying on transformation invariants. Our approach can accommodate any degree of descriptors thus modeling any kind of potential deformation according to the needs of each specific problem. Other potential descriptors suc...

Full description

Saved in:
Bibliographic Details
Main Authors: Tsolakis, A., Falelakis, M., Delopoulos, A.
Format: Conference Proceeding
Language:English
Subjects:
Colored noise
Computational complexity
Computer vision
Deformable models
Eigenvalues and eigenfunctions
Explosions
Labeling
Noise robustness
Polynomials
Stability
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We propose a formulation for solving the point pattern correspondence problem, relying on transformation invariants. Our approach can accommodate any degree of descriptors thus modeling any kind of potential deformation according to the needs of each specific problem. Other potential descriptors such as color or local appearance can also be incorporated. A brief study on the complexity of the methodology is made which proves to be inherently polynomial while allowing for further adjustments via thresholding. Initial experiments on both synthetic and real data demonstrate its potentials in terms of accuracy and robustness to noise and outliers.
ISSN:1051-4651
2831-7475
DOI:10.1109/ICPR.2008.4761227