Detecting branching structures using local gaussian models
UNSPECIFIED (2002) Detecting branching structures using local gaussian models. In: IEEE International Symposium on Biomedical Imaging, WASHINGTON, D.C., JUL 07-10, 2002. Published in: 2002 IEEE INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING, PROCEEDINGS pp. 161-164.Full text not available from this repository.
We present a method for modelling and estimating branching structures, such as blood vessel bifurcations, from medical images. Branches are modelled as a superposition of Gaussian functions in a local region which describe the amplitude, position and orientations of intersecting linear features. The centroids of component features are separated by applying K-means to the local Fourier phase and the covariances and amplitudes subsequently estimated by a likelihood maximisation. We employ a penalised likelihood test (AIC) to select the best fit model in a region. Results are presented on synthetic and representative 2D retinal images which show the estimation to be robust and accurate in the presence of noise. We compare our results with a curvature scale-space operator method.
|Item Type:||Conference Item (UNSPECIFIED)|
T Technology > TK Electrical engineering. Electronics Nuclear engineering
|Journal or Publication Title:||2002 IEEE INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING, PROCEEDINGS|
|Number of Pages:||4|
|Page Range:||pp. 161-164|
|Title of Event:||IEEE International Symposium on Biomedical Imaging|
|Location of Event:||WASHINGTON, D.C.|
|Date(s) of Event:||JUL 07-10, 2002|
Actions (login required)