Title :
A convolutional neural architecture: an application for defects detection in continuous manufacturing systems
Author :
Calderon-Martinez, Jose A. ; Campoy-Cervera, P.
Abstract :
One of the most important and critical aspects in all manufacturing processes is product inspection. Neural network based systems allow a compromise between resolution and processing speed in automatic inspection. This work introduces the development of a neural architecture, named Convolutional Top-Down Spiral Architecture, used to automatically generate digital filters for artificial vision inspection systems. Experimental results of this architecture applied for the detection of defects over paper pulp images gathered in a real environment are presented.
Keywords :
automatic optical inspection; convolution; digital filters; image recognition; manufacturing processes; neural net architecture; paper industry; artificial vision inspection systems; automatic digital filter generation; automatic inspection; continuous manufacturing systems; convolutional top-down spiral architecture; defects detection; manufacturing processes; neural networks based systems; paper pulp images; product inspection; Convolution; Digital filters; Image analysis; Image resolution; Inspection; Manufacturing systems; Neural networks; Neurons; Paper pulp; Pixel;
Conference_Titel :
Circuits and Systems, 2003. ISCAS '03. Proceedings of the 2003 International Symposium on
Print_ISBN :
0-7803-7761-3
DOI :
10.1109/ISCAS.2003.1206421
