Abstract. Automatic visual inspection has become an important application of pattern recognition, as it supports the human in this demanding and often dangerous work. Nevertheless,...
Abstract. Most of the processing in vision today uses spatially invariant operations. This gives efficient and compact computing structures, with the conventional convenient separa...
We propose an unsupervised “local learning” algorithm for learning a metric in the input space. Geometrically, for a given query point, the algorithm finds the minimum volume ...
A large body of research in machine learning is concerned with supervised learning from examples. The examples are typically represented as vectors in a multi-dimensional feature ...
We describe a method for predicting user intentions as part of a human-robot interface. In particular, we show that funnels, i.e., geometric objects that partition the input space...
Michael T. Rosenstein, Andrew H. Fagg, Shichao Ou,...