An Efficient Feature Point Registration Method for Retinal Images
Abstract
Image registration is a fundamental problem to several image processing and computer vision applications. In the case of medical imaging, disease diagnosis and treatment planning are often supported by multiple images acquired from the same patient. Image registration techniques, hence, are needed in order to integrate the information gained from several images to obtain a comprehensive understanding. A broad range of image registration methods has been proposed for different medical imaging applications including retinal image registration. In this paper, we have developed a robust registration algorithm for estimating a rigid transformation using genetic algorithms. The aim is to develop a highly accurate and automated feature point image registration method of retinal images. Feature detection is first performed based on vessel blood segmentation using the Kirsch edge operator, followed by a matching process. Then for registration, we have adopted a genetic algorithm as an optimization method to estimate the optimal parameters of the rigid transformation. The simulation results have shown that this method is really efficient for registration of retinal images.
Keywords
Full Text:
PDFRefbacks
- There are currently no refbacks.
Disclaimer/Regarding indexing issue:
We have provided the online access of all issues and papers to the indexing agencies (as given on journal web site). It’s depend on indexing agencies when, how and what manner they can index or not. Hence, we like to inform that on the basis of earlier indexing, we can’t predict the today or future indexing policy of third party (i.e. indexing agencies) as they have right to discontinue any journal at any time without prior information to the journal. So, please neither sends any question nor expects any answer from us on the behalf of third party i.e. indexing agencies.Hence, we will not issue any certificate or letter for indexing issue. Our role is just to provide the online access to them. So we do properly this and one can visit indexing agencies website to get the authentic information.