Title :
Global-to-local shape priors for variational image segmentation
Author :
Last, C. ; Winkelbach, S. ; Wahl, F.M.
Author_Institution :
Inst. fuer Robot. und Prozessinf., Tech. Univ. Braunschweig, Braunschweig, Germany
Abstract :
One major problem, when using statistical shape information in image segmentation problems, is that many training samples are needed in order to obtain a satisfactory shape prior for a particular class, especially when the intra-class variability of the object shapes is high. To cope with this problem, we present an elegant variational formulation that allows local adaptations of the parameters associated with a trained shape prior. This enables us to obtain accurate segmentation results with a limited amount of training shapes. We provide a sound mathematical foundation for our approach and embed it into the well-known level set segmentation framework, which makes our approach applicable to a large class of problems. Moreover, we show how a smooth transition from global to local adaptations of the shape parameters can be achieved. We point out the advantages of our new variational global-to-local approach by comparing it with another level set segmentation approach that includes a global shape prior.
Keywords :
image sampling; image segmentation; learning (artificial intelligence); mathematical analysis; statistical analysis; global-to-local shape parameter; intraclass object shapes variability; sound mathematical foundation; statistical shape information; training sample; variational image segmentation; well-known level set segmentation framework; Active contours; Equations; Image segmentation; Level set; Mathematical model; Shape; Training; image segmentation; level set methods; local adaptation; statistical shape priors; variational methods;
Conference_Titel :
Image Processing (ICIP), 2014 IEEE International Conference on
Conference_Location :
Paris
DOI :
10.1109/ICIP.2014.7026222