Invariant Multi-scale Object Categorisation and Recognition

Authors:
João Rodrigues;J. M. Buf
Affiliations:
University of the Algarve --- Escola Superior Tecnologia, Faro, Portugal;University of the Algarve --- Vision Laboratory --- FCT, Faro, Portugal
Venue:
IbPRIA '07 Proceedings of the 3rd Iberian conference on Pattern Recognition and Image Analysis, Part I
Year:
2007

Citing 3
Cited 0

Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
Learning invariant object recognition in the visual system with continuous transformations

Biological Cybernetics
Face recognition by cortical multi-scale line and edge representations

ICIAR'06 Proceedings of the Third international conference on Image Analysis and Recognition - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

Object recognition requires that templates with canonical views are stored in memory. Such templates must somehow be normalised. In this paper we present a novel method for obtaining 2D translation, rotation and size invariance. Cortical simple, complex and end-stopped cells provide multi-scale maps of lines, edges and keypoints. These maps are combined such that objects are characterised. Dynamic routing in neighbouring neural layers allows feature maps of input objects and stored templates to converge. We illustrate the construction of group templates and the invariance method for object categorisation and recognition in the context of a cortical architecture, which can be applied in computer vision.