Learning to Recognize Three Dimensional Objects

Abstract

A learning account for the problem of object recognition is developed within the probably approximately correct (PAC) model of learnability. The key assumption underlying this work is that objects can be recognized (or discriminated) using simple representations in terms of syntactically simple relations over the raw image. Although the potential number of these simple relations could be huge, only a few of them are actually present in each observed image, and a fairly small number ofthose observed are relevant to discriminating an object. We show that these properties can be exploited to yield an efficient learning approach in terms of sample some intermediate representations extracted from the image. We evaluate this approach in a large-scale experimental study in which the SNoW learning architecture is and computational complexity within the PAC model. No assumptions are needed on the distribution of the observed objects, and the learning performance is quantified relative to its experience. Most important, the success of learning an object representation is naturally tied to the ability to represent it as a functionof used to learn representations for the 100 objects in the Columbia Object Image Library. Experimental results exhibit good generalization and robustness properties of the SNoW-based method relative to other approaches. SNoWs recognition rate degrades more gracefully when the training data contains fewer views, and it shows similar behavior in some preliminary experiments with partially occluded objects.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2002
Accession Number
AD1019290

Entities

People

  • Dan Roth
  • Ming-Hsuan Yang
  • Narendra Ahuja

Organizations

  • University of Illinois Urbana–Champaign

Tags

Communities of Interest

  • Autonomy
  • Energy and Power Technologies
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Algorithms
  • Artificial Intelligence
  • Artificial Intelligence Software
  • Automata Theory
  • Computer Languages
  • Computer Vision
  • Information Processing
  • Information Science
  • Information Systems
  • Kernel Functions
  • Machine Learning
  • Neural Networks
  • Object Recognition
  • Pattern Recognition
  • Probabilistic Models
  • Supervised Machine Learning
  • Three Dimensional

Fields of Study

  • Computer science

Readers

  • Computer Vision.
  • Neural Network Machine Learning.
  • Theoretical Analysis.