Self-Organizing Map for Hyperspectral Image Analysis

  • Authors:

  • Pablo Martínez Cobo;Pedro Luis Aguilar Mateos;Rosa M. Pérez Utrero;Marino Linaje Trigueros;Juan Carlos Preciado;Antonio Plaza

  • Affiliations:

  • -;-;-;-;-;-

  • Venue:
  • IWANN '01 Proceedings of the 6th International Work-Conference on Artificial and Natural Neural Networks: Bio-inspired Applications of Connectionism-Part II
  • Year:
  • 2001

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper we present a neural network methodology used for classifying an hyperspectral image referencied as Indian Pines. The network Parameters (learning and neighborhood function) are adjusted using a test battery generated from the image, selecting the values that give the best robustness and discrimination capacity. The availity of ground truth allows us to introduce a new stadistical measure to quantity the resulting classification accuracy. The results of this methodology show an accuracy of 80% in the classification.