Blackledge, JonathanDubovitskiy, D. A.John Collomosse and Ian Grimstead2014-01-312014-01-312010978-3-905673-75-3https://doi.org/10.2312/LocalChapterEvents/TPCG/TPCG10/131-138A unique space oriented filer is presented in order to detect and isolate the cell of a nucleus for applications in cytopathology. A classification method for nuclei is then considered based on the application of a set of features which includes certain fractal parameters. Segmentation algorithms are considered in which a self-adjustable sharpening filter is designed to enhance object location. Although the methods discussed and the algorithms developed have a range of applications, in this work we focus on the engineering of a system for automating a Papanicolaou screening test using standard optical imagesCategories and Subject Descriptors (according to ACM CCS): I.5.4 [Pattern recognition]: Segmentation, Contour detection, Decision making, Self-learning, Cytopathology