Statistical Object Recognition

To be practical, recognition systems must deal with uncertainty. Positions of image features in scenes vary. Features sometimes fail to appear because of unfavorable illumination. In this work, methods of statistical inference are combined with empirical models of uncertainty in order to evaluate an...

Full description

Saved in:
Bibliographic Details
Main Author: Wells, III, William M
Format: Report
Language:English
Subjects:
ALGORITHMS
COMPUTER VISION
Cybernetics
ILLUMINATION
MATHEMATICAL MODELS
MEAN EDGE IMAGES
OBJECT RECOGNITION
PATTERN RECOGNITION
PROBABILITY
STATISTICAL INFERENCE
Statistics and Probability
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:To be practical, recognition systems must deal with uncertainty. Positions of image features in scenes vary. Features sometimes fail to appear because of unfavorable illumination. In this work, methods of statistical inference are combined with empirical models of uncertainty in order to evaluate and refine hypotheses about the occurrence of a known object in a scene. Probabilistic models are used to characterize image features and their correspondences. A statistical approach is taken for the acquisition of object models from observations in images: Mean Edge Images are used to capture object features that are reasonably stable with respect to variations in illumination.