In a previous paper [1] we showed that a 3D object can be digitized without changing the topology if the object is r-regular and if the reconstruction method fulfills certain requ...
We propose a competitive finite mixture of neurons (or perceptrons) for solving binary classification problems. Our classifier includes a prior for the weights between different n...
Karthik Sridharan, Matthew J. Beal, Venu Govindara...
We present a framework that enables the use of traditional feature selection algorithms in a new context - for building a set of subsets of specified properties. During the course...
This paper introduces an effective initialization approach for segmentation using the Chan-Vese model. The initial curve is found by searching among the extremals of the fidelity ...
Jan Erik Solem, Niels Chr. Overgaard, Anders Heyde...
A method is proposed for performing shape analysis of m-surfaces, e.g. planar curves and surfaces, with a geometric interpretation. The analysis uses an implicit surface represent...
Extracting human postural information from video sequences has proved a difficult research question. The most successful approaches to date have been based on particle filtering, ...
We describe a new expression database which contains video sequences of both played and natural expressions and an expression classification system based on warped optical flow fi...
James Skelley, Robert Fischer, Arup Sarma, Bernd H...
In this work we propose a probabilistic model for generic object classification from raw range images. Our approach supports a validation process in which classes are verified usi...
This paper deals with the analysis of broadcast soccer video. To recognize interesting events such as a goal, estimation of ball movements is necessary. It is, however, sometimes ...
Jun Miura, Takumi Shimawaki, Takuro Sakiyama, Yosh...
The performance of the fingerprint identification and verification systems relies heavily on the quality of the input fingerprint images. In this paper, we propose an effective im...