Title
SIFT Vs SURF: Quantifying the Variation in Transformations.
Abstract
This paper studies the robustness of SIFT and SURF against different image transforms (rigid body, similarity, affine and projective) by quantitatively analyzing the variations in the extent of transformations. Previous studies have been comparing the two techniques on absolute transformations rather than the specific amount of deformation caused by the transformation. The paper establishes an exhaustive empirical analysis of such deformations and matching capability of SIFT and SURF with variations in matching parameters and the amount of tolerance. This is helpful in choosing the specific use case for applying these techniques.
Year
Venue
Field
2015
CoRR
Affine transformation,Scale-invariant feature transform,Computer vision,Pattern recognition,Computer science,Rigid body,Robustness (computer science),Artificial intelligence,Deformation (mechanics)
DocType
Volume
Citations 
Journal
abs/1504.06740
0
PageRank 
References 
Authors
0.34
2
1
Name
Order
Citations
PageRank
Siddharth Srivastava195.89