---
title: "Natural Object Recognition: A Theoretical Framework and Its Implementation"
authors:
  - "Thomas M. Strat"
  - "Martin A. Fischler"
doi: ""
url: "https://ijcai.org/proceedings/1991/186"
pdf: "https://ijcai.org/proceedings/1991/0186.pdf"
venue: "Proceedings of the Twelfth International Joint Conference on Artificial Intelligence"
year: 1991
pages: "1264-1269"
track: "Vision"
keywords:
---

# Natural Object Recognition: A Theoretical Framework and Its Implementation

Thomas M. Strat, Martin A. Fischler

*Proceedings of the Twelfth International Joint Conference on Artificial Intelligence*, pages 1264-1269.

## Abstract

Most work in visual recognition by computer has focused on recognizing objects by their geomett·ic shape, or by the presence or absence of some prespecified co ll ection of locally measurable attributes (e.g., spectral reflectance, texture, or distinguished markings). On the other hand, most entities in the natural world defy compact description of their shapes, and have no characteristic features with discriminatory power. As a result, image-understanding research has achieved little swress toward recognition in natural scenes. We offer a fundamentally new approach to visual recognition that avoids these limitations and has been used to recognize trees, bushes, grass, and trails in ground-level scenes of a natural environment.