Click here to view fulltext PDF

Permanent link:
https://www.ias.ac.in/article/fulltext/sadh/037/06/0709-0721

Gerschgorin circle; Gerschgorin bound; covariance matrix; eigenvalues; normalized cross-correlation; magnetic resonance images (MRI).

In this paper, an efficient similarity measure technique is proposed for medical image registration. The proposed approach is based on the Gerschgorin circles theorem. In this approach, image registration is carried out by considering Gerschgorin bounds of a covariance matrix of two compared images with normalized energy. The beauty of this approach is that there is no need to calculate image features like eigenvalues and eigenvectors. This technique is superior to other well-known techniques such as normalized cross-correlation method and eigenvalue-based similarity measures since it avoids the false registration and requires less computation. The proposed approach is sensitive to small defects and robust to change in illuminations and noise. Experimental results on various synthetic medical images have shown the effectiveness of the proposed technique for detecting and locating the disease in the complicated medical images.

Vilas H Gaidhane¹ Yogesh V Hote² Vijander Singh¹

1. Department of Instrumentation and Control Engineering, Netaji Subhas Institute of Technology, University of Delhi, New Delhi, 110 078 India
2. Department of Electrical Engineering, Indian Institute of Technology, Roorkee, 247 667 India

Published

December 2012

Manuscript received

19 January 2012

Manuscript revised

31 July 2012

Accepted

6 September 2012