Title :
Line-end detection and boundary gap completion in an EDANN module for orientation
Author :
Van Hulle, M.M. ; Tollenaere, T. ; Orban, G.A.
Author_Institution :
Lab. voor Neuro- en Psychofysiologie, Katholieke Univ., Leuven, Belgium
Abstract :
Explores two sources of inaccuracies originating from the use of local line detectors for inferring curve and boundary traces: (1) due to the position uncertainty of the local line detectors, ends of thin lines are not easily detected, even if cross-orientation inhibition is applied; and (2) due to the limited ability of the local line detectors to assess more global trace information gaps appear in the curve and boundary extracted. It is shown how a single EDANN (entropy drive artificial neural networks) module processing the orientation of illumination contrast compensates for these inaccuracies by performing a two-stage detection process, a competitive and a cooperative one. In the competitive stage, a vector field of tangents to curves and boundaries is extracted by using elongated receptive fields. In the cooperative stage, line-ends are extracted and boundary gaps are bridged by broadening the neuron´s orientation tuning curves
Keywords :
computer vision; computerised picture processing; neural nets; EDANN module; boundary gap completion; boundary traces; competitive process; computer vision; cooperative process; curve traces; early vision; entropy drive artificial neural networks; local line detectors; neuron´s orientation tuning curves; orientation; Artificial neural networks; Brain modeling; Data mining; Detectors; Electronic design automation and methodology; Entropy; Laboratories; Lighting; Neurons; Visual system;
Conference_Titel :
Neural Networks, 1991. 1991 IEEE International Joint Conference on
Print_ISBN :
0-7803-0227-3
DOI :
10.1109/IJCNN.1991.170597