Sciweavers

Share
SIBGRAPI
2003
IEEE

Learning-Based versus Model-Based Log-Polar Feature Extraction Operators: A Comparative Study

8 years 9 months ago
Learning-Based versus Model-Based Log-Polar Feature Extraction Operators: A Comparative Study
In this paper, we compare two distinct primal sketch feature extraction operators: one based on neural network feature learning and the other based on mathematical models of the features. We tested both kinds of operator with a set of known, but previously untrained, synthetic features and, while varying their classification thresholds, measured the operator’s false acceptance and false rejection errors. Results have shown that the model-based approach is more unstable and unreliable than the learning-based approach, which presented better results with respect to the number of correctly classified features.
Herman Martins Gomes, Robert B. Fisher
Added 05 Jul 2010
Updated 05 Jul 2010
Type Conference
Year 2003
Where SIBGRAPI
Authors Herman Martins Gomes, Robert B. Fisher
Comments (0)
books