A Theory of Multiscale, Curvature-Based Shape Representation for Planar Curves
IEEE Transactions on Pattern Analysis and Machine Intelligence
Shape representation and recognition from multiscale curvature
Computer Vision and Image Understanding
Neural Networks: A Comprehensive Foundation
Neural Networks: A Comprehensive Foundation
Fast correspondence-based system for shape retrieval
Pattern Recognition Letters
Recognition of Shapes by Editing Their Shock Graphs
IEEE Transactions on Pattern Analysis and Machine Intelligence
Detecting Objects of Variable Shape Structure With Hidden State Shape Models
IEEE Transactions on Pattern Analysis and Machine Intelligence
A visual pathway for shape-based invariant classification of gray scale images
Integrated Computer-Aided Engineering - Artificial Neural Networks
Path Similarity Skeleton Graph Matching
IEEE Transactions on Pattern Analysis and Machine Intelligence
Disconnected Skeleton: Shape at Its Absolute Scale
IEEE Transactions on Pattern Analysis and Machine Intelligence
Visual pathways for detection of landmark points
ICANN'06 Proceedings of the 16th international conference on Artificial Neural Networks - Volume Part I
Retrieval by shape similarity with perceptual distance andeffective indexing
IEEE Transactions on Multimedia
| Hi-index | 0.00 |
The Medial Axis Transform (MAT) (or skeleton transform) is one of the most studied shape representation techniques with established advantages for general 2D shape recognition. Embedding local boundary information in the skeleton, in particular, has been shown to improve 2D shape recognition capability to state of the art levels. In this paper we present a visual pathway for extracting an analogous to the MAT skeleton abstraction of shape that also contains local boundary curvature information. We refer to this structure with the term curvature-skeleton. The proposed architecture is inspired by the biological findings regarding the cortical neurons of the visual cortex and their special purpose Receptive Fields (RFs). Points of high curvature are initially identified and subsequently combined by means of a visual pathway that achieves an analogous to the MAT abstraction of shape but also embeds in the skeleton local curvature information of the shape's boundary. We present experimental results illustrating that such an abstraction can improve the recognition capability of multi layered neural network classifiers.