15th Annual British Machine Vision Conference (BMVC 2004)

British Machine Vision Conference

British Machine Vision Conference

In the context of part segmentation from 2D edge images, this paper presents some interesting results with a novel method that addresses the problem of ltering a redundant set of part hypotheses that retains only those that are likely to correspond to actual parts. In the proposed method, supporting evidence for hypotheses are put in competition in a Minimum Description-Length (MDL) framework t...

British Machine Vision Conference 1

Accurate registration of surfaces is a common problem in computer vision. Several algorithms exist to reene an approximate value for the pose to an accurate value. They are all more or less variants of the Iterated Closest Point algorithm of Besl and McKay (1992). Up to now the problem of determining the uncertainty in the pose estimate thus obtained has not been addressed in detail. In this pa...

British Machine Vision Conference ( a )

We describe several established error of t (EOF) functions for use in the least square tting of ellipses, and introduce a further four new EOFs. Four measures are given for assessing the suitability of such EOFs, quantifying their linearity, curvature bias, asymmetry, and overall goodness. These measures enable a better understanding to be gained of the individual merits of the EOF functions.

British Machine Vision Conference 2000

This edition of the IVC journal is devoted to some of the top-rated papers from BMVC2000, the 11th British Machine Vision Conference, hosted by the University of Bristol in September 2000. The conference coincided with a fuel shortage crisis, but there were no delegate cancellations and there were even some new registrations on the ®rst day. Altogether there were around 150 delegates from all o...