Published Articles >> Table of Contents >> Abstract

Fifth International Conference on Computer Vision (ICCV'95)   p. 786
Probabilistic visual learning for object detection
B. Moghaddam, Media Lab., MIT, Cambridge, MA, USA
A. Pentland, Media Lab., MIT, Cambridge, MA, USA

Full Article Text:

DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/ICCV.1995.466858
Send link to a friend

Abstract
We present an unsupervised technique for visual learning which is based on density estimation in high-dimensional spaces using an eigenspace decomposition. Two types of density estimates are derived for modeling the training data: a multivariate Gaussian (for a unimodal distributions) and a multivariate Mixture-of-Gaussians model (for multimodal distributions). These probability densities are then used to formulate a maximum-likelihood estimation framework for visual search and target detection for automatic object recognition. This learning technique is tested in experiments with modeling and subsequent detection of human faces and non-rigid objects such as hands.
Back to Top Additional Information
Index Terms- object recognition; unsupervised learning; maximum likelihood estimation; probabilistic visual learning; object detection; unsupervised visual learning; density estimation; high-dimensional spaces; eigenspace decomposition; training data; multivariate Gaussian; probability densities; maximum-likelihood estimation; visual search; target detection; automatic object recognition; human faces; nonrigid objects Citation:  B. Moghaddam, A. Pentland, "Probabilistic visual learning for object detection," iccv, p. 786,  Fifth International Conference on Computer Vision (ICCV'95),  1995