Statistical shape models have been extensively used in several image analysis problems, providing accurate estimates of object boundaries. However, their performance degrades if the object of interest is surrounded by a cluttered background, and the features extracted from the image contain outliers. Under these assumptions, most deformable models fail since they are attracted towards the outli...

A new method for shape analysis of X-ray images of human hand bones for estimation of bone maturity is proposed. To handle low contrast and non-uniformity of X-ray images, we design stable pre-processings to enhance images. The contour extraction method is based on local force control of a connected contour for deforming so as to fit it to an outline of a piece of bone. As a result with real im...

Shape matrices have been used as a representation of planar shapes like industrial parts or printed characters. In this paper, we investigate the use of shape matrices as a mixed shape factor for off-line signature verification. By mixed shape factor we mean any global shape factor where the position of local measurements are take into account in the definition of a similarity measure between t...

Automatic delineation of the prostate boundary in transrectal ultrasound (TRUS) can play a key role in image-guided prostate intervention. However, it is a very challenging task for several reasons, especially due to the large variation of the prostate shape from the base to the apex. To deal with the problem, a new method for incrementally learning the patient-specific local shape statistics i...

Docking simulates molecular interactions. Protein protein docking, owing to the sizes of molecules, is a very challenging problem. As the number of degrees of freedom in the molecular structure of proteins is huge, docking algorithms consider the molecules as relatively rigid bodies. Shape matching of two protein molecules is computationally difficult because the possibilities of matching the m...

This work discusses an ongoing project for hands gesture recognition in computer vision systems. The proposed approach is based on the shape analysis tools introduced in [1]. More specifically, the wavelet transform will be used for generating features for the recognition of hand gestures based on contours.

Natural objects can be subject to various transformations yet still preserve properties that we refer to as invariants. Here, we use definitions of affine-invariant arclength for surfaces in R in order to extend the set of existing non-rigid shape analysis tools. We show that by re-defining the surface metric as its equi-affine version, the surface with its modified metric tensor can be treated...

A specimen of Holohalaelurus shark (Scyliorhinidae; Chondrichthyes) recently collected off southern Mozambique, represents a southward range extension of 2200km for the recently described, H. grennian Human 2006. This specimen presents not only a significant extension of its known distribution, but is also only the second female specimen known for this species. Moreover, the specimen exhibits m...

This paper presents a methodology for shape analysis of anatomical structures. A template shape is used as a unit, and a shape transformation mapping the template to a particular structure is used to quantify the shape of the structure with respect to the template. The geometric characteristics of the boundaries of the template and of an individual structure are used to deene corresponding regi...

Shape recognition is a challenging task when images contain overlapping, noisy, occluded, partial shapes. This paper addresses the task of matching input shapes with model shapes described in terms of features such as line segments and angles. The quality of matching is gauged using a measure derived from attributed shape grammars. We apply genetic algorithms to the partial shape-matching task....