Where Data Meets Computer Science
Header

Ellipse

In this project we introduce a new method for the detection of parametrisable shapes in N dimensions; this method has been developed for ellipses and uses simple morphological operations, building on aspects of granulometry and signal processing techniques. With this method it is possible to easily extract the position, size and rotation of elliptical objects in any image data. This method is low parameter, accurate and robust to noise and object clustering in greyscale images; key contributions are the abiltiy to find an unknown number of ellipses with no a priori information and no arbitrary thresholding and robustness to both noise and clustering.

Orientation of determined major axis at every pixel.

Orientation of determined major axis
at every pixel.

Collaborators:

  • Prof John Girkin, Department of Physics, University of Durham, UK
  • Prof. Roy Quinlan, School of Biological & Biomedical Sciences, University of Durham, UK

Publications: