Design and implementation of a parallel geographically weighted -nearest neighbor classifier.

The development of high-performance classifiers represents an important step in improving the timeliness of remote sensing classification in the era of high spatial resolution. Geographically weighted -nearest neighbors (gw-NN)-a classifier that incorporates spatial information into the traditional -NN classifier-has demonstrated to be better at mitigating salt-and-pepper noise and misclassification. However, the integration of spatial dependence relationships into spectral information is computationally intensive.