抄録
Pattern classification of image data is one of the most important processing in the analysis of remote sensing image. Different classification results may be obtained when different classification methods are applied to the same image data or a fixed classification method is applied to different image data. Therefore it is necessary to find a criterion to assess the different classification results. In order to assess the different classification results the criterion called“Equivocation Quantification”is proposed. However there are some problems to be resolved in the application of equivocation quantification. To resolve part of the problems existing in the equivocation quantification a new assessment criterion of classification results of image pattern called“Fuzzy Set Quantification”is proposed in this paper. And equivocation quantification and fuzzy set quantification are computed with classification score based on mathematical models. The calculation results with both assessment criteria are compared and the efficiency of fuzzy set quantification is also described.
