Share Email Print
cover

Proceedings Paper

Automatic image registration algorithm based on improved Harris corner detection
Author(s): Tengyuan Zhang; Yuesong Mei
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper 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.

Paper Details

Date Published: 1 October 2011
PDF: 5 pages
Proc. SPIE 8285, International Conference on Graphic and Image Processing (ICGIP 2011), 82853S (1 October 2011); doi: 10.1117/12.914468
Show Author Affiliations
Tengyuan Zhang, Beijing institute of technology (China)
Yuesong Mei, Beijing institute of technology (China)


Published in SPIE Proceedings Vol. 8285:
International Conference on Graphic and Image Processing (ICGIP 2011)

© SPIE. Terms of Use
Back to Top