Improving Hyperspectral Image Classification Method for Fine Land Use Assessment Application Using Semisupervised Machine Learning

Table 2

Overall accuracy and Kappa coefficient based on comparison of the varying classification methods.

Classification methods	Iteration time (s)	Overall accuracy (%)	Kappa coefficient
-means classifier	18	52.58%	0.41
Minimum distance classifier	12	80.56%	0.75
Neural network classifier	151	92.78%	0.90
Support vector machine classifier	30	95.23%	0.93
Semisupervised classifier	60	97.31%	0.96