A. Bhalerao and R. Wilson, \Estimating local and global image structure using a gaussian intensity model," Medical Image Understanding and Analysis, 2001.  Home/Search   Document Details and Download   Summary   Related Articles

....are presented in Section 5. Conclusions and ideas on how to extend the algorithm follow in Section 6. 2 Local Linear Feature Estimation 2. 1 A Gaussian Intensity Feature Model If an ideal linear feature is windowed by a smooth function w( it can be regarded as a 2 dimensional Gaussian function [14], examples of which are shown in Figure 1. The 2 dimensional Gaussian function can be written in the form: G( x) 2 ) 1=2 jCj 1=2 exp( x ) T C 1 ( x ) 2) 1) 2 where x is the spatial co ordinate, i.e. x = x; y) T (2) and is the mean vector and the covariance matrix C = ....

....image. However, due to the in uence of the noise, localisation errors still exist for real data. This approach is still in its initial stages. The next step is to consider some ways of simultaneous tting super posed models to reduce the e ects of noise to get better accuracy of the localisation [14]. Another development would be generalising the model including a classi er in order to explicitly label the junction. Furthermore, a neighbourhood linking strategy to track vessels between the branch point could be employed to extract the entire tree structure. We model the data over a range of ....

A. Bhalerao and R. Wilson, \Estimating local and global image structure using a gaussian intensity model," Medical Image Understanding and Analysis, 2001.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC