Title :
Evolutive algorithms pioneering neural networks training for artificial vision applications
Author :
Seijas, Juan ; Sanz-González, José L.
Author_Institution :
SENER Ingenieria y Sistemas SA, Madrid, Spain
fDate :
27 Jun-2 Jul 1994
Abstract :
A straightforward method for implementing a neural network (NN) solution in the field of image processing, for attitude and position determination, is presented in this paper. The proposed evolutive training algorithm is capable of setting the appropriate dimension of the neural network and the adequate weights interconnecting the neurons. The recommended solution is based on simulation results
Keywords :
computer vision; learning (artificial intelligence); neural nets; evolutive training algorithm; image processing; machine vision; neural networks; neurons interconnecting weights; Artificial neural networks; Backpropagation algorithms; Cameras; Charge coupled devices; Charge-coupled image sensors; Image processing; Lenses; Neural networks; Neurons; Position measurement;
Conference_Titel :
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1901-X
DOI :
10.1109/ICNN.1994.374429
