- Abstract:
-
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 know, 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.
- Copyright:
- Copyright 2003 IEEE. Reprinted from Proc XVI Brazilian Symposium on Computer Graphics and Image Processing (SIBGRAPI), San Carlos, Brazil.
- This material is posted here with permission of the IEEE.Such permission of the IEEE does not in any way imply IEEE endorsement of any of Edinburgh's products or services. Internal or personal use of thismaterial is permitted. However, permission to reprint/republish this materialfor advertising or promotional purposes or for creating new collective worksfor resale or redistribution must be obtained from the IEEE by writing to pubs-permissions@ieee.org. By choosing to view this document, you agree to all provisions of the copyright laws protecting it.
- Links To Paper
- No links available
- Bibtex format
- @InProceedings{EDI-INF-RR-0780,
- author = {
Herman Gomes
and Robert Fisher
},
- title = {Learning-based versus model-based log-polar feature extraction operators: a comparative study},
- book title = {Proc XVI Brazilian Symposium on Computer Graphics and Image Processing (SIBGRAPI)},
- publisher = {IEEE Computer Society Press},
- year = 2003,
- month = {Oct},
- pages = {299-306},
- }
|
