An improved image matching algorithm based on SURF and Delaunay TIN

Yuan-ming Cheng; Peng-gen Cheng; Xiao-yong Chen; Shou-zhu Zheng

doi:10.1117/12.2207665

9 December 2015 An improved image matching algorithm based on SURF and Delaunay TIN

Yuan-ming Cheng, Peng-gen Cheng, Xiao-yong Chen, Shou-zhu Zheng

Proceedings Volume 9808, International Conference on Intelligent Earth Observing and Applications 2015; 980811 (2015) https://doi.org/10.1117/12.2207665
Event: International Conference on Intelligent Earth Observing and Applications, 2015, Guilin, China

Abstract

Image matching is one of the key technologies in the image processing. In order to increase its efficiency and precision, a new method for image matching which based on the improved SURF and Delaunay-TIN is proposed in this paper. Based on the original SURF algorithm, three constraint conditions, color invariant model, Delaunay-TIN, triangle similarity function and photography invariant are added into the original SURF model. With the proposed algorithm, the image color information is effectively retained and the erroneous matching rate of features is largely reduced. The experimental results shows that this proposed method has the characteristics of higher matching speed, uniform distribution of feature points to be matched, and higher correct matching rate than the original algorithm does.

Citation Download Citation

Yuan-ming Cheng, Peng-gen Cheng, Xiao-yong Chen, and Shou-zhu Zheng "An improved image matching algorithm based on SURF and Delaunay TIN", Proc. SPIE 9808, International Conference on Intelligent Earth Observing and Applications 2015, 980811 (9 December 2015); https://doi.org/10.1117/12.2207665

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