A new approach to medical image stitching using minimum average correlation energy filter and peak to side-lobe ratio

Authors:
S. Salbiah;A. Somaya;H. Arof;Z. S. Saleh;F. Ibrahim
Affiliations:
Department of Electrical Engineering, University of Malaya, 50603 Kuala Lumpur, Malaysia;Department of Electrical Engineering, University of Malaya, 50603 Kuala Lumpur, Malaysia;Department of Electrical Engineering, University of Malaya, 50603 Kuala Lumpur, Malaysia;Department of Electrical Engineering, University of Malaya, 50603 Kuala Lumpur, Malaysia;Department of Biomedical Engineering, University of Malaya, 50603 Kuala Lumpur, Malaysia
Venue:
International Journal of Imaging Systems and Technology
Year:
2012

Citing 6
Cited 0

A survey of image registration techniques

ACM Computing Surveys (CSUR)
Correlation Pattern Recognition

Correlation Pattern Recognition
Image alignment and stitching: a tutorial

Foundations and Trends® in Computer Graphics and Vision
MOCC: a fast and robust correlation-based method for interest point matching under large scale changes

EURASIP Journal on Advances in Signal Processing
Correlation filters for facial recognition login access control

PCM'04 Proceedings of the 5th Pacific Rim conference on Advances in Multimedia Information Processing - Volume Part I
Signal detection by complex spatial filtering

IEEE Transactions on Information Theory

Quantified Score

Hi-index	0.00

Visualization

Abstract

Standard X-ray images using conventional screen-film technique have a limited field of view and failed to visualize the entire long bone on a single image. To produce images with whole body parts, digitized images from the films that contain portions of the body parts are assembled using image stitching. This article presents a new medical image stitching method that uses minimum average correlation energy filters to identify and merge pairs of X-ray medical images. The effectiveness of the proposed method is demonstrated in the experiments involving two databases that contain a total of 40 pairs of overlapping and nonoverlapping images. Then the experimental results are compared to those of the normalized cross correlation (NCC) method. It is found that the proposed method outperforms the NCC method in identifying both the overlapping and nonoverlapping medical images. The efficacy of the proposed method is further vindicated by its average execution time which is about five times shorter than that of the NCC method. © 2012 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 22, 166–171, 2012 © 2012 Wiley Periodicals, Inc.