An Axis-Based Representation for Recognition

TL;DR

This paper introduces an axis-based shape representation that is invariant to scale, rotation, and small viewpoint changes, improving shape recognition by capturing perceptual qualities and avoiding skeleton instability.

Contribution

The paper proposes a novel axis-based shape description and matching framework that enhances recognition robustness and perceptual relevance over traditional skeleton methods.

Findings

Successful shape recognition on diverse 2D shape database

Representation is invariant to scale, rotation, and small viewpoint changes

Avoids common instability issues of traditional skeletons

Abstract

This paper presents a new axis-based shape representation scheme along with a matching framework to address the problem of generic shape recognition. The main idea is to define the relative spatial arrangement of local symmetry axes and their metric properties in a shape centered coordinate frame. The resulting descriptions are invariant to scale, rotation, small changes in viewpoint and articulations. Symmetry points are extracted from a surface whose level curves roughly mimic the motion by curvature. By increasing the amount of smoothing on the evolving curve, only those symmetry axes that correspond to the most prominent parts of a shape are extracted. The representation does not suffer from the common instability problems of the traditional connected skeletons. It captures the perceptual qualities of shapes well. Therefore finding the similarities and the differences among shapes becomes easier. The matching process gives highly successful results on a diverse database of 2D shapes.