Abstract
We present a new data-driven feature-point registration method for image sequences. This method is based on a modified Kohonen network model that performs local non-affine transformations based on a point's neighbourhood context. This new method is ideal for non-real time applications where the situation is too complex to enable an operational modelling of the transformations needed for a point-to-point mapping from one image into another such as in contrast-enhanced sequences of MRI-mammogramms. This new method is compared to existing approaches. The results of tests with different types of grey-value images are discussed.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
