Abstract. Fuzzy segmentation methods have been developed in order to reduce the negative effects of the unavoidable loss of data in the digitization process. These methods require the development of new image analysis methods, handling grey-level images. This paper describes the first step in our work on developing shape analysis methods for fuzzy images: the investigation of several measurements on digitized objects with fuzzy borders. The performance of perimeter, area, and the P 2 A measure estimators for digitized disks and digitized squares with fuzzy borders is analyzed. The method we suggest greatly improves the results obtained from crisp (hard) segmentation, especially in the case of low resolution images.