Research on multi-pixels edge detecting and matching

Yu Liu; Yan-jun Li; Ke Zhang; You-yi Jiang

doi:10.1117/12.725345

11 January 2007 Research on multi-pixels edge detecting and matching

Yu Liu, Yan-jun Li, Ke Zhang, You-yi Jiang

Proceedings Volume 6279, 27th International Congress on High-Speed Photography and Photonics; 62792N (2007) https://doi.org/10.1117/12.725345
Event: 27th International congress on High-Speed Photography and Photonics, 2006, Xi'an, China

Abstract

Aiming at the influence of geometrical deformation on image matching, the method based on gray-level difference between the nearby pixels detecting multi-pixels edge of image is put forward. To a 256 by 256 image, it needs only 0.14 second to detect edge which is 40% and 35% faster respectively than that of the Prewitt and Robert arithmetic. Applying the method based on multi-pixels edge character to image matching, the influences of edge excursion can be improved obviously: when excursion exists in single pixel point, the relative probability of image matching is improved to 67%; when it exits in edge, it is improved to 50%. Research shows that this method is of simple model, high real-time quality and anti-geometrical-deformation. Most importantly, it is simply conducted.

Citation Download Citation

Yu Liu, Yan-jun Li, Ke Zhang, and You-yi Jiang "Research on multi-pixels edge detecting and matching", Proc. SPIE 6279, 27th International Congress on High-Speed Photography and Photonics, 62792N (11 January 2007); https://doi.org/10.1117/12.725345

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