eng URI http://hdl.handle.net/10795/3281 σύστημα πληροφορικής εφαρμογή της πληροφορικής επεξεργασία δεδομένων ιατρικές επιστήμες This paper presents a novel framework for unsupervised level set parameterization using multi-scale filtering. A standard multi-scale, directional filtering algorithm is used in order to capture the orientation coherence in edge regions. The latter is encoded in entropy-based image `heatmaps', which are able to weight forces guiding level set evolution. Experiments are conducted on two large benchmark databases as well as on real proteomics images. The experimental results demonstrate that the proposed framework is capable of accelerating contour convergence, whereas it obtains a segmentation quality comparable to the one obtained with empirically optimized parameterization. 5 pp. LOMv1.0 creator LOMv1.0 publisher LOMv1.0 Scientific Coordinator LOMv1.0 Project Executing Organisation 2013-07 Digital Library of the Operational Programme "Education and Lifelong Learning" abstract types Text Entropy codes Filtering theory Image segmentation Medical image processing Proteomics 684795 application/pdf http://repository.edulll.gr/edulll/bitstream/10795/3281/2/3281_1.154_%ce%91%ce%9d_3_7_13.pdf URI http://hdl.handle.net/10795/3281 LOMv1.0creator 2016-05-19T11:19:35Z LOMv1.0validator 2016-05-19T11:19:35Z LOMv1.0 gre no no Copyright EYD-EPEDBM (Operational Programme "Education and Lifelong Learning")