Shape Characterization via Boundary Distortion
This work addresses shape analysis for computer vision applications, but it appears incremental as it builds on existing transformation-based methods.
The paper tackled the problem of shape characterization by deriving new shape descriptors based on directional analysis and transformations, resulting in a rotation-, reflection-, translation-, and scaling-invariant metric with demonstrated accuracy on shape retrieval tasks across two databases.
In this paper, we derive new shape descriptors based on a directional characterization. The main idea is to study the behavior of the shape neighborhood under family of transformations. We obtain a description invariant with respect to rotation, reflection, translation and scaling. A well-defined metric is then proposed on the associated feature space. We show the continuity of this metric. Some results on shape retrieval are provided on two databases to show the accuracy of the proposed shape metric.