In this paper a DTCNN-based vision system for pattern recognition in an artificial vision architecture is illustrated. The bipolar images, segmented in a preprocessing stage, constitute the input to a cellular associative memory in the recognizing stage of the vision system. The performance of DTCNNs designed as associative memories is confirmed by means of examples of detection and recognition of tools handled by a robot in an assembly line.
On the Performance of CNNs for Associative Memories in Robot Vision Systems / Brucoli, M.; Cafagna, D.; Carnimeo, Leonarda. - (2001), pp. 341-345. [10.1109/ISCAS.2001.921317]
On the Performance of CNNs for Associative Memories in Robot Vision Systems
CARNIMEO, Leonarda
2001-01-01
Abstract
In this paper a DTCNN-based vision system for pattern recognition in an artificial vision architecture is illustrated. The bipolar images, segmented in a preprocessing stage, constitute the input to a cellular associative memory in the recognizing stage of the vision system. The performance of DTCNNs designed as associative memories is confirmed by means of examples of detection and recognition of tools handled by a robot in an assembly line.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
