This paper introduces a still image segmentation technique based on an active contour obtained via single-layer CNNs. The contour initially laid on the frame of the image shrinks, deforms and multiplies until it matches the edges of each of the objects present in the scene. The shape of each object in the image is accurately extracted and nested objects, if any, are correctly detected. Experimental measures of the accuracy of the segmentation were carried out using the Hausdorff distance
2D Still-image segmentation with CNN-Amoeba / G., Iannizzotto; F., La Rosa; Rizzo, Alessandro; M. G., Xibilia. - (2003), pp. 24-31. (Intervento presentato al convegno IEEE International Workshop on Computer Architecture for Machine Perception, CAMP2003 tenutosi a New Orleans, LA, USA nel May 12-16, 2003) [10.1109/CAMP.2003.1598145].
2D Still-image segmentation with CNN-Amoeba
RIZZO, Alessandro;
2003-01-01
Abstract
This paper introduces a still image segmentation technique based on an active contour obtained via single-layer CNNs. The contour initially laid on the frame of the image shrinks, deforms and multiplies until it matches the edges of each of the objects present in the scene. The shape of each object in the image is accurately extracted and nested objects, if any, are correctly detected. Experimental measures of the accuracy of the segmentation were carried out using the Hausdorff distanceI documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
