Title :
A cooperative network for contour grouping
Author :
Mangin, Frank ; Berthod, Marc ; Zerubia, Josiane
Author_Institution :
INRIA Sophia-Antipolis, Valbonne, France
fDate :
30 Aug-3 Sep 1992
Abstract :
A new iterative algorithm for edge intensity image enhancement is proposed. It uses local cooperation-inhibition processes to produce an edge image in which the most relevant contours have reached maximal activation, and small gaps and junctions have been filled in. Implementation on a massively parallel machine has provided high speed performances, and results of experimentations with real scene images are presented. The algorithm is robust in complex edge image context, and is perfectly stable under any number of iterations
Keywords :
edge detection; iterative methods; contour grouping; cooperative network; edge detection; edge intensity image enhancement; iterative algorithm; local cooperation-inhibition processes; massively parallel machine; maximal activation; Data mining; Detectors; Digital images; Filters; Image edge detection; Image enhancement; Iterative algorithms; Layout; Pixel; Robustness;
Conference_Titel :
Pattern Recognition, 1992. Vol.III. Conference C: Image, Speech and Signal Analysis, Proceedings., 11th IAPR International Conference on
Conference_Location :
The Hague
Print_ISBN :
0-8186-2920-7
DOI :
10.1109/ICPR.1992.201988