A New Biologically Motivated Framework for Robust Object Recognition

Abstract

In this paper,we introduce a novel set of features for robust object recognition, which exhibits outstanding performances on a variety of object categories while being capable of learning from only a few training examples. Each element of this set is a complex feature obtained by combining position- and scale-tolerant edge-detectors over neighboring positions and multiple orientations. Our system motivated by a quantitative model of visual cortex outperforms state-of-the-art systems on a variety of object image datasets from different groups. We also show that our system is able to learn from very few examples with no prior category knowledge. The success of the approach is also a suggestive plausibility proof for a class of feed-forward models of object recognition in cortex. Finally, we conjecture the existence of a universal overcomplete dictionary of features that could handle the recognition of all object categories.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Nov 01, 2004
Accession Number
ADA454724

Entities

People

  • Lior Wolf
  • Thomas Serre
  • Tomaso Poggio

Organizations

  • Massachusetts Institute of Technology

Tags

Communities of Interest

  • Air Platforms
  • Biomedical
  • C4I

DTIC Thesaurus Topics

  • Aircrafts
  • Artificial Intelligence
  • Artificial Intelligence Software
  • Automata Theory
  • Birds
  • Cognitive Science
  • Computer Programs
  • Computer Science
  • Computer Vision
  • Computers
  • Detection
  • Image Recognition
  • Machine Learning
  • Object Recognition
  • Object-Oriented Database Management Systems
  • Recognition
  • Test Sets

Fields of Study

  • Computer science

Readers

  • Computer Vision.
  • Neural Network Machine Learning.