Interactive object detection using a fuzzy image segmentation approach

• Autorzy: Mari M. , Smits P. C. , Kieś P. , Chmielewski L.
• Języki publikacji: EN

Abstrakty

EN

In this paper the attention is focused on the processing of digital images, in particular on the segmentation of medical images. A new 3D fuzzy segmentation technique is presented to outline the adventages of a relatively simple software tool that may help the user to find contours of the objects of interest in images. The proposed technique is based on a seed growing approach, which takes into account both contextual and topological information in the image. The uncertainty of the image is considered through the use of fuzzy measures, well suited to represent the characteristics of a medical image. The result is a set of possible contours for the volume of interest at different certainty values. They mey be viewed as alternative comtours of the same object. If the method is used interactively, the user has the possibility to scroll very quickly through the different contours to select the most appropriate one for a specific application, according to his own knowledge.

Słowa kluczowe

EN

image processing; fuzzy conectedness; optimal path; isoregion; MR imaging

• Wydawca: Institute of Information Technology of the Warsaw University of Life Sciences – SGGW
• Czasopismo: Machine Graphics and Vision
• Rocznik: 1998
• Tom: Vol. 7, No. 4
• Strony: 765--780
• Opis fizyczny: Bibliogr. 11 poz.

Twórcy

autor

Mari M.

autor

Smits P. C.

autor

Kieś P.

autor

Chmielewski L.

• University of Genoa, Department of Biophysical and Electronic Engineering, via all'Opera Pia 11A, I-16145, Genova, Italy