Simple Object Recognition Using Shape-from-Shading

Philip L. Worthington         Benoit Huet         Edwin R. Hancock
Department of Computer Science, University of York, UK
{plw,huetb,erh}@minster.cs.york.ac.uk

Introduction

This tutorial is derived from a paper presented at ICPR98 and a poster at BMVC98. We investigate the use of shape-from-shading for object recognition. The local surface orientation information recovered using shape-from-shading is shown to provide useful input to a simple appearance-based object recognition scheme. We consider two representations which may be recovered from shading information - the needle-map, and the local curvature shape-index - and examine their relative performance for object recognition. Specifically, we use a histogram-comparison technique, and focus upon the relative stability of the representations to small changes of viewpoint. We demonstrate that the needle-map representation allows the view-sphere to be spanned using a significantly smaller number of characteristic views than using either the raw images or the shape index.

 

• Introduction
• Shape from Shading
• Characteristic Views
• Using SFS for Object Recognition
• Direct Use of Needle-Map
• The Shape Index
• Experiments
• Future Work
• Bibliography
• About this document ...