Search

Visual processing tasks often require the matching of contours in two images. Examples include determining image motion and matching features for object recognition. We propose a scheme that takes partial constraints on the matching between contours in two images and finds the matches between these contours using local affine transformations. This new scheme is motivated in part by existing ideas for both recovering optical flow and matching features for object recognition, and in part by short-term motion processing in the primate visual system. The scheme assumes that contours are locally approximated by orthographic projections of planar objects. A local affine transformation is determined for each contour point using oriented elliptical Gaussian neighborhoods that smoothly integrate information over proximally connected contours at several spatial scales. At the largest scale satisfying available constraints a minimal solution mechanism employs a modified pseudoinverse to directly predict matches that are closest to the simplest purely translational correspondence. Using this scheme, the matches for points along contours can be determined in parallel without iteration. The scheme's matching performance is assessed by simulation om noisy synthetic and natural contour imagery.

Different approaches to visual object recognition can be divided into two general classes: model-based vs. non model-based schemes. In this paper we establish some limitation on the class of non model-based recognition schemes. a non model-based scheme is based on functions invariant to viewing position and illumination conditions. We show that every function that is invariant to viewing position of all objects is the trivial (constant) function. The same result holds even if the recognition function is not required to be perfect, but is allowed to make mistakes and misidentify each object from a substantial fraction of viewing directions. It follows that every consistent recognition scheme for recognizing Three dimensional objects must in general be model based. We then consider recognition schemes restricted to classes of objects and show that, for some classes, the only consistent recognition function is still the trivial function. For other classes (such as the class of symmetric objects) a nontrivial recognition scheme exists. We define the notion of a discrimination power of a consistent recognition function for a class of objects. The function's discrimination power determines the set of objects that can be discriminated by the recognition function. We show that it is possible to determine the upper bound of the function's discrimination power for every consistent recognition function., Sponsored in part by Contract N00014-85-K-0124 and Grant NSF-IRI89-00267.

This paper presents a model for the general flow of processing in the neocortex. The basic process, called 'sequence-seeking,' is a search for a sequence of mappings, or transformations, linking source and target representations. The search is bi-directional, 'bottom-up' as well as 'top-down, ' and it explores in parallel a large number of alternative sequences. This operation is implemented in a structure termed 'counter streams,' in which multiple sequences are explored along two separate, complementary pathways which seeking to meet. The first part of the paper discusses the general sequence- seeking scheme and a number of related processes, such as the learning of successful sequences, context effects, and the use of 'express lines' and partial matches. The second part discusses biological implications of the model in terms of connections within and between cortical areas. The model is compared with existing data, and a number of new predictions are proposed.