Groupwise Non-rigid Image Alignment With Graph-based Initialisation

dc.contributor.authorAal-Yhia, Ahmaden_US
dc.contributor.authorMalcolm, Paulen_US
dc.contributor.authorAkanyeti, Otaren_US
dc.contributor.authorZwiggelaar, Reyeren_US
dc.contributor.authorTiddeman, Bernarden_US
dc.contributor.editor{Tam, Gary K. L. and Vidal, Francken_US
dc.date.accessioned2018-09-19T15:15:01Z
dc.date.available2018-09-19T15:15:01Z
dc.date.issued2018
dc.description.abstractGroupwise image alignment automatically provides non-rigid registration across a set of images. It has found applications in facial image analysis and medical image analysis by automatically generating statistical models of shape and appearance. The main approaches used previously include iterative and graph-based approaches. In iterative approaches, the registration of each image is iteratively updated to minimise an error measure across the set. Various metrics and optimisation strategies have been proposed to achieve this. Graph-based methods perform registration of each pair of images in the set, to form a weighted graph of the ''distance'' between all the images, and then finds the optimal paths between the most central image and every other image. In this paper, we use a graph-based approach to perform initialisation, which is then refined with an iterative approach. Pairwise registration is performed using demons registration, then shortest paths identified in the resulting graph are used to provide an initial warp for each image by concatenating warps along the path. The warps are refined using an iterative Levenberg-Marquardt minimisation to the mean, based on updating the locations of a small number of points and incorporating a stiffness constraint. This optimisation approach is efficient, has very few free parameters to tune and we show how to tune the few remaining parameters. We compare the combined approach to both the iterative and graph-based approaches used independently. Results demonstrate that the combined method improves the alignment of various datasets, including two face datasets and a difficult medical dataset of prostate MRI images.en_US
dc.description.sectionheadersVision and Learning
dc.description.seriesinformationComputer Graphics and Visual Computing (CGVC)
dc.identifier.doi10.2312/cgvc.20181203
dc.identifier.isbn978-3-03868-071-0
dc.identifier.pages15-21
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/cgvc20181203
dc.identifier.urihttps://doi.org/10.2312/cgvc.20181203
dc.publisherThe Eurographics Associationen_US
dc.subjectComputing methodologies
dc.subjectComputer vision
dc.subjectMatching
dc.subjectImage processing
dc.titleGroupwise Non-rigid Image Alignment With Graph-based Initialisationen_US
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
015-021.pdf
Size:
1.53 MB
Format:
Adobe Portable Document Format