We develop a new formulation for including invariance in a general form of the Hough transform. We first develop a formal definition of the Hough transform mapping for arbitrary s...
We describe a neural network which enhances and completes salient closed contours. Our work is different from all previous work in three important ways. First, like the input prov...
Abstract. In this paper we propose a new approach to recognize symbols by the use of a concept lattice. We propose to build a concept lattice in terms of graphical patterns. Each m...
We describe an unsupervised learning algorithm for extracting sparse and locally shift-invariant features. We also devise a principled procedure for learning hierarchies of invari...
—A new type of global stability is introduced and its equivalent Lyapunov characterization is presented. The problem of global stability of the compact set composed by all invari...