Detection of heart-contour in chest X-ray images

OData support
Dr. Horváth Gábor
Department of Measurement and Information Systems

Heart shadow segmentation in chest radiographs is the first step in compensating for the intensity of the heart shadow, in order to aid medical experts and certain algorithms by enabling better identification of medical symptoms and signs of disease in the heart shadow area. In this BSc thesis the classical Active Shape Model (ASM) introduced by (C. J Taylor Oct 2001) is revisited through scale-independently designed filters within the scale-space framework. The notion of shape adaptable edge detection introduced by (Jacob and Unser 2004) is also applied through the use of a scale-independent steerable wedge detector filter, which can be seen as a more generalized form of the Canny edge detector filter. And finally an edge detection method is presented that makes extensive use of wedge detector filters and considerations from scale-space theory.


Please sign in to download the files of this thesis.