Hypothesis Generation and Verification using Complex Feedback Strategies for Object Recognition (1996)
| Citations: | 1 - 1 self |
BibTeX
@TECHREPORT{Mirmehdi96hypothesisgeneration,
author = {M. Mirmehdi and P L Palmer and J. Kittler and H Dabis},
title = {Hypothesis Generation and Verification using Complex Feedback Strategies for Object Recognition},
institution = {},
year = {1996}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
We develop a paradigm for feedback strategies that combine low-level features to produce a focus of attention mechanism, and a high-level object model to direct search for missing information. The aim of this complex feedback strategy is to find instances of a generic class of objects by improving on established single-pass hypothesis generation and verification approaches. We argue that a complex feedback strategy is required for this problem to produce optimal sets of low level features to reduce the number of hypotheses generated. The feedback further enables updated sets of features to be extracted so that the target object may be located even in very noisy data. The use of an interest operator in the feedback directs the search through the hypotheses in an optimal manner, so minimising the amount of feedback to false alarms. Furthermore, we aim to obtain detailed information about a complex object and not just its location. Thus, following top-down recognition of the object our fe...
