Automatic image registration algorithm based on improved Harris corner detection

Tengyuan Zhang; Yuesong Mei

doi:10.1117/12.914468

1 October 2011 Automatic image registration algorithm based on improved Harris corner detection

Tengyuan Zhang, Yuesong Mei

Proceedings Volume 8285, International Conference on Graphic and Image Processing (ICGIP 2011); 82853S (2011) https://doi.org/10.1117/12.914468
Event: 2011 International Conference on Graphic and Image Processing, 2011, Cairo, Egypt

Abstract

Image registration, as an important part the computer image processing, has been widely used in such technologies as video compression, 3D reconstruction, image restoration, etc. The paper proposes a new improved Harris algorithm based on corner detection. Based on the characteristics of changes in gray gradient of corners, the paper puts forward the concept of level of similarity of image scale pixel. By detecting the level of similarity between the gray value of the center point of the window and other pixels in the neighborhood, the paper accurately wipes off the pixels without calculating CRF, excludes non-corner pixels and determines the candidate corners. Then calculates the candidate corners through CRF, obtains the final corner, calculates affine transformation coefficient, and completes the image registration. The experiments show that the algorithm can ensure accuracy, and at the same time, reduce calculation to a great extent, and improve the speed of calculation, so that the automatic image registration can be quickly and effectively achieved, which can help the application in real-time processing.

Citation Download Citation

Tengyuan Zhang and Yuesong Mei "Automatic image registration algorithm based on improved Harris corner detection", Proc. SPIE 8285, International Conference on Graphic and Image Processing (ICGIP 2011), 82853S (1 October 2011); https://doi.org/10.1117/12.914468

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