The full text of this article/chapter:
Fuzzy-genetic cell boundary extraction in medical images
by George Karkavitsas, Maria Rangoussi
12th International Workshop on Systems, Signals and Image Processing (IWSSIP), Vol. 1, No. 1, 2005
Abstract: Object detection and localization is the first step in various digital image processing tasks. Furthermore, object boundary extraction is of importance for the image segmentation and pattern classification steps that typically follow, aiming towards an automated image understanding and interpretation system. In a medical imaging context, the later will assist the human expert in the task of diagnosis. The present work focuses on medical images taken through a microscope, containing different types of objects (cells) in a uniform background (serum). A genetic algorithm is employed for the detection and localization of objects of a certain type within the image. As a second step, boundary extraction and boundary representation by chain coding are achieved through a proposed algorithm, which incorporates fuzzy elements as to the direction decisions made during boundary tracking. This type of decision-making allows for detailed and accurate boundary extraction without pre-smoothing. Satisfactory results are obtained from the application of the proposed scheme on a set of sixteen blood cell images, showing the potential our approach for handling object images in general.
is only available to individual subscribers or to users at subscribing institutions.
Pay per view: If you are not a Subscriber and you just want to read the full contents of this article, please click here to purchase online access to the full-text of this article. Please allow 3 days + mailing time. Current price for article is US$38.00
Members of the Editorial Board or subscribers of the 12th International Workshop on Systems, Signals and Image Processing (IWSSIP), that have been redirected here, please click here if you have IP-authentication access, or check if you have a registered username/password subscription with Inderscience. If that is the case, please Login: