Appearance Based Qualitative Image Description for Object Class Recognition
J Thuresson and Stefan Carlsson
Springer Lecture Notes in Computer Science Volume 3022, pp. 518-529, 2004.

Abstract

Abstract. The problem of recognizing classes of objects as opposed to special instances requires methods of comparing images that capture the variation within the class while they discriminate against objects outside the class. We present a simple method for image description based on histograms of qualitative shape indexes computed from the combination of triplets of sampled locations and gradient directions in the image. We demonstrate that this method indeed is able to capture variation within classes of objects and we apply it to the problem of recognizing four di

PDF - Requires Adobe Acrobat Reader or other PDF viewer.

[Edit]