This paper illustrates a new object-oriented segmentation algorithm based on the CNN paradigm. The approach, which exploits rigorous model of the image contours, presents two remarkable features: i) it provides more accurate segmented objects than the ones obtained by other CNN-based techniques; ii) it makes use of CNN templates that take into account the hardware characteristics imposed by the CNNUM. Results carried out for benchmark video sequences highlight the capabilities of the proposed technique.
New object-oriented segmentation algorithm based on the CNN paradigm / Grassi, G.; Vecchio, P.; DI SCIASCIO, Eugenio; Grieco, Luigi Alfredo. - In: IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS. II, EXPRESS BRIEFS. - ISSN 1549-7747. - 53:4(2006), pp. 259-263. [10.1109/TCSII.2005.859571]
New object-oriented segmentation algorithm based on the CNN paradigm
DI SCIASCIO, Eugenio;GRIECO, Luigi Alfredo
2006-01-01
Abstract
This paper illustrates a new object-oriented segmentation algorithm based on the CNN paradigm. The approach, which exploits rigorous model of the image contours, presents two remarkable features: i) it provides more accurate segmented objects than the ones obtained by other CNN-based techniques; ii) it makes use of CNN templates that take into account the hardware characteristics imposed by the CNNUM. Results carried out for benchmark video sequences highlight the capabilities of the proposed technique.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.