Stereoscopic disparity plays an important role in the processing and compression of 3-D imagery. For example, dense disparity fields are used to reconstruct intermediate (varying-viewpoint) images. Although for small camera baselines dense disparity can be reliably estimated using gradient-based methods, this is not the case for large baselines due to the violation of underlying assumptions (e....

The first task of a programmer who wants to understand how a certain feature is implemented is to localize the implementation of the feature in the code. If the implementations of a set of related features are to be understood, a programmer is interested in their commonalities and variabilities. For large and badly documented programs, localizing features in code and identifying commonalities a...

A novel method to obtain correspondence between landmarks when comparing pairs of mammographic images from the same patient is presented. Our approach is based on automatically established correspondence between linear structures (i.e. ducts and vessels) which appear in mammograms using robust features such as orientation, width and curvature extracted from those structures. In addition, a nove...

This paper presents an empirical study of affine invariant feature detectors to perform matching on video sequences of people with non-rigid surface deformation. Recent advances in feature detection and wide baseline matching have focused on static scenes. Video frames of human movement capture highly non-rigid deformation such as loose hair, cloth creases, skin stretching and free flowing clot...

Object recognition is the process of identifying the types and locations of objects in the image. Earlier work has shown the desirability of using fuzzy compatibility for local feature correspondence and fuzzy clustering for pose estimation of two-dimensional objects. This paper extends the methodology to images of three dimensional objects by applying geometric invariants, specifically the cro...

In this paper we develop a novel MRF formulation for calculating sparse features correspondence in image pairs. Our MRF terms can include cliques of variable sizes, and solve these using Loopy Belief Propagation. To calculate our MRF topology we develop a variant of the K-means algorithm which we call the KN-means algorithm (where each mean has a specified number of neighbours). The method is c...

A class of image-matrix-based feature extraction algorithms has been discussed earlier. The correspondence argues that 2-D principal component analysis and Fisher linear discriminant (FLD) are equivalent to block-based PCA and FLD. In this correspondence, we point out that this statement is not rigorous.

Current methods for planar segmentation of binocular images require either calibrating the cameras or having correct stereo correspondence a priori. Here are introduced robust and extendable frameworks, that bypass these requirements. Feature vectors represent image structure, and ideas from scale space theory are applied. Two basic frameworks are introduced, one requiring (possibly partially i...

In this paper, we present an efficient multi-scale similarity matching method for shape-based image indexing and retrieval. This method is affine-invariant and stable against noise and shape deformations. Shapes which have undergone mirror reflection can also be retrieved in a unified manner. In this approach, similarity matching is cast as correspondence matching of two shapes which is then so...