Scale-invariant global sparse image matching method based on Delaunay triangle

Hong Zhang; Lei Wang; Ruiming Jia

doi:10.1117/12.832804

30 October 2009 Scale-invariant global sparse image matching method based on Delaunay triangle

Hong Zhang, Lei Wang, Ruiming Jia

Proceedings Volume 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis; 74953S (2009) https://doi.org/10.1117/12.832804
Event: Sixth International Symposium on Multispectral Image Processing and Pattern Recognition, 2009, Yichang, China

Abstract

This paper presents an approach of global sparse matching algorithm based on Delaunay Triangle theory to obtain reliable matching result of detected feature points between images. Our approach can solve the matching problem in the case of images captured under a certain range of scaling, rotation and translation, together with image affine distortion, addition of noise, and change in illumination. Considering that it is hard to obtain a high percentage of correct matched point pairs, we present this kind of Delaunay Triangle based matching method to improve the accuracy and exactness of matching result. First, corner detection algorithms are proposed to obtain accurate location of feature points. Then the relation of the feature points is constructed according to the Delaunay Triangle Theory in the form of a triangle net. Therefore, the feature points matching problem is transformed into a node angle and length vector matching problem in the triangle net. During the matching procession, the gray information of the image has not been used. The experimental results show that the method could achieve accurate matching results with a better percentage of correction.

Citation Download Citation

Hong Zhang, Lei Wang, and Ruiming Jia "Scale-invariant global sparse image matching method based on Delaunay triangle", Proc. SPIE 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis, 74953S (30 October 2009); https://doi.org/10.1117/12.832804

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available