]> 2026-04-04T20:33:55+02:00 Publications:Learning Accurate Active Contours 500 en <p>Focus of research in Active contour models (ACM) area is mainly on development of various energy functions based on physical intuition. In this work, instead of designing a new energy function, we generate a multitude of contour candidates using various values of ACM parameters, assess their quality, and select the most suitable one for an object at hand. A random forest is trained to make contour quality assessments.We demonstrate experimentally superiority of the developed technique over three known algorithms in the P. minimum cells detection task solved via segmentation of phytoplankton images.</p> 14th International Conference, EANN 2013, Halkidiki, Greece, September 13-16 http://dx.doi.org/10.1007/978-3-642-41013-0_41 http://hh.diva-portal.org/smash/record.jsf?searchId=1&pid=diva2:668670 405 Engineering Applications of Neural Networks : 14th International Conference, EANN 2013, Halkidiki, Greece, September 13-16, 2013 Proceedings, Part I Conference Paper Communications in Computer and Information Science ; 383 396 Learning Accurate Active Contours 2013 2016-09-30T20:41:35Z 2457662.3622106 Learning Accurate Active Contours 500 0 plainlist list 1 [[:Publications:Learning Accurate Active Contours]] Learning Accurate Active Contours# QUERY10e1cf30474d53abbf431ee16d489c27 500 [2,"smw-datavalue-property-restricted-annotation-use","Publisher"] Learning Accurate Active Contours# ERR6c155b5d70b69ddb590b4f2e73389c2a 500 [2,"smw-datavalue-property-restricted-annotation-use","Author"] Learning Accurate Active Contours# ERRe24f17e090c98448f3de99d03182b7b6