A Comparison and Rating of Conditioned Bayesian Discriminant Classifiers:by Quantitative Term of Training Representability

概要

論文の詳細を見る
Representability of training areas is primarily focused on its qualitative spectrum features. But it was revealed by this study that the representability by a quantitative application of prior frequencies of each land-cover item also plays an important role for more accurate classification in remote sensing, increasing the rate by ten to fifteen percent for the whole scene in pixel-by-pixel evaluation.<BR>Complete enumeration for accuracy assessment in test field was realized such that detailed digital land-use data of 10 m×10 m resolution, prepared by the Japanese Geographical Survey Institute, were aggregated to 50 m×50 m cell size in match for geocoded Landsat MSS pixels.<BR>Changing the sampling sizes in the merged file, coupled with eight application types of Bayesian discriminant method, produced sixteen systemat-ically-conditioned classifiers to compare, and resulted that there is a great variation of accuracies by the classifier especially in terms of the applicable suitabilities in case of separating individual land-cover items.
社団法人日本リモートセンシング学会の論文