SEaTH - A new tool for automated feature extraction in the context of object-oriented image analysis

In order to avoid the time-consuming trial-and-error practice for seeking significant features for optimal class separation in object-based classification, an automatic feature extraction methodology, called SEaTH has been developed. SEaTH calculates the SEperability and the corresponding THresholds of object classes for any number of given features on the basis of a statistical approach. The statistical measure for determining the representative features for each object class is the mutual separability of the object classes. Subsequently, SEaTH calculates those thresholds which allow the best separability in the selected features. The methodology and its application to a case study on an Iranian nuclear facility are presented. With regard to the automation of object-based image processing, aspects of standardization and transferability are discussed.