Self-organizing maps
Hi-index | 0.00 |
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.