In this paper a fast method of selecting a neural network architecture for pattern recognition tasks is presented. We demonstrate that our proposed method of selecting both input ...
This paper tackles the problem of obtaining a good initial set of corner matches between two images without resorting to any constraints from motion or structure models. Several d...
We tackle the problem of object recognition using a Bayesian approach. A marked point process [1] is used as a prior model for the (unknown number of) objects. A sample is generat...
A new geometrical approach in solving the shape from shading problem of Lambertian model is discussed. It is shown that this problem is bound by two local constraints through the ...
The least squares method is the most commonly used technique for fitting an ellipse through a set of points. However, it has a low breakdown point, which means that it performs p...