Thresholding method to estimate a total number of data

Abstract

Thresholding method is a general tool for classification of a population. This method is one of the picture binarization techniques. Various thresholding methods have been proposed by many researchers. Some methods proposed by Dr. Otsu and Dr. Kittler et al or Dr. Kurita have a very simple algorithm and are very easy for data handling, and these techniques have been applied for a lot of classification analysis. These are effective methods for increasing the overall accuracy of analysis. however, there are some cases in which these methods are not appropriate for a population analysis. For example, this is a case of which objective of analysis is to select a threshold to estimate the total number of data (pixels) of each classified population. In particular, If there is significant difference between the total numbers or/and variances of two populations, error possibilities in classification differ excessively from each other. Consequently, estimated total number of each classified population could be very different from the actual one. In this report, authors propose a new method which could be applied to select a threshold to estimate the total number of data more precisely in the above mentioned case. And authors verify the applicability of the new method by comparing results which are obtained with existing method and the new method. Both simulated sample data and actual satellite's data are utilized in the analysis.