View-Based Models of 3D Object Recognition and Class-Specific Invariance
Abstract
This paper describes the main features of a view-based model of object recognition. The model tries to capture general properties to be expected in a biological architecture for object recognition. The basic module is a regularization network in which each of the hidden units is broadly tuned to a specific view of the object to be recognized. Object recognition, Vision and learning, View-based recognition, Biological vision.
Document Details
- Document Type
- Technical Report
- Publication Date
- Apr 01, 1994
- Accession Number
- ADA279858
Entities
People
- Anya Hurlbert
- Nikos K. Logothetis
- Thomas Vetter
- Tomaso Poggio
Organizations
- Massachusetts Institute of Technology