Title :
Cellular Neural Networks for Object-oriented Segmentation
Author :
Grassi, Giuseppe ; Vecchio, Pietro
Author_Institution :
Dipt. Ingegneria Innovazione, Univ. degli Studi di Lecce
Abstract :
By exploiting the cellular neural network paradigm, this paper present a new object-oriented segmentation algorithm that takes into account the hardware characteristics of the cellular neural networks universal machine. In particular, by using a rigorous model of the image contours, this paper focuses on the edge extraction phase as well as on the performance evaluations. Simulation results, carried out for Stefan, coast guard, car-phone and football video sequences, show the effectiveness of the approach developed herein
Keywords :
cellular neural nets; edge detection; image segmentation; image sequences; object recognition; Stefan video sequence; car-phone video sequence; cellular neural networks; coast guard video sequence; edge extraction; football video sequence; image contour; object-oriented segmentation; universal machine; Cellular neural networks; Computational modeling; Computer networks; Image processing; Image segmentation; MPEG 4 Standard; Neural network hardware; Object oriented modeling; Turing machines; Video sequences;
Conference_Titel :
Research in Microelectronics and Electronics 2006, Ph. D.
Conference_Location :
Otranto
Print_ISBN :
1-4244-0157-7
DOI :
10.1109/RME.2006.1689944
