It has been a while since I last updated this blog. But today I finally found the time to do it and share another presentation summary with you.
This time the summary is about the paper “Multiresolution Elastic Matching” from Ruzena Bajcsy and Stane Kovačič.
The summary introduction goes as follows:
The general idea behind the work presented in”Multiresolution Elastic Matching” is to develop a mechanism to match “an explicit 3-dimensional pictorial model to locally variant data”.In other words, two existing representations (one model representation and one input representation) are put into correspondence. To achieve this goal,rigid transforms are used to account for global misalignments, while elastic deformations are appliedfor local shape differences. A coarse-to-fine strategy(called multiresolution elastic matching) is the heart of the presented paper and leads to more efficient computations and improved convergence of the matching process in general.
You can find the summary here: Multiresolution Elastic Matching – a summary.