Chapter 1: Invited Addresses and Tutorials on Signals, Coding,
  Systems and Intelligent Techniques

Title: Fuzzy-genetic cell boundary extraction in medical images

Author(s): George Karkavitsas, Maria Rangoussi

Address: Department of Electronics, Technological Education Institute of Piraeus 250, Thivon str., GR-12244, Aigaleo-Athens, Greece | Department of Electronics, Technological Education Institute of Piraeus 250, Thivon str., GR-12244, Aigaleo-Athens, Greece

Reference: 12th International Workshop on Systems, Signals and Image Processing pp. 125 - 128

Abstract/Summary: 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.

Order a copy of this article