The objects location from images binarized by means of self-learning neural network

  • Authors:

  • Vincenzo Niola;Giuseppe Quaremba;Sergio Savino

  • Affiliations:

  • Department of Mechanical Engineering for Energetics, University of Naples "Federico II", Napoli, Italy;University of Naples "Federico II", Napoli, Italy;University of Naples "Federico II", Napoli, Italy

  • Venue:
  • NN'05 Proceedings of the 6th WSEAS international conference on Neural networks
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

The present work represents a first approach for the realization of a methodology for objects location and recognition. The choice objects was the starting point of the study; it has been decided to consider nuts and bolts of various dimensions. Then in order to eliminate the noise added to the images a neural network was designed. Once the desired pictures were obtained, an algorithm, based on the theory of the fuzzy sets, was applied, for detecting the position of each objects. The instruments used were low cost: a digital camera, one stand, equipped with four lamps assuring, for each acquisition, a diffused lighting system, one personal computer.