Title :
A new object-oriented segmentation algorithm based on CNNs - part I: edge extraction
Author :
Grass, Giuseppe ; Di Sciascio, Eugenio ; Grieco, Alfredo L. ; Vecchio, Pietro
Author_Institution :
Dipt. Ingegneria Innovazione, Univ. di Lecce, Italy
Abstract :
By using the CNN paradigm, this paper and the companion one (Grasi et al., 2005) present a new object-oriented segmentation algorithm, which takes into account the hardware characteristics imposed by the CNNUM. In particular, by exploiting a rigorous model of the image contours, this paper focuses on CNN algorithms for edge extraction. Simulation results show that the approach provides more accurate edge extractions than the ones obtained by other CNN-based techniques.
Keywords :
cellular neural nets; edge detection; image segmentation; object detection; cellular neural networks universal machine; edge extraction; hardware characteristics; image contours; object-oriented segmentation; Cellular neural networks; Computer networks; Engines; Hardware; Image processing; Image segmentation; MPEG 4 Standard; Object oriented modeling; Turing machines; Video sequences;
Conference_Titel :
Cellular Neural Networks and Their Applications, 2005 9th International Workshop on
Print_ISBN :
0-7803-9185-3
DOI :
10.1109/CNNA.2005.1543185
