Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/84199
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Conference paper |
Title: | The distinctiveness, detectability, and robustness of local image features |
Author: | Carneiro, G. Jepson, A. |
Citation: | Proceedings, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, vol. 2 / C. Schmid, S. Soatto, and C. Tomasi (eds.): pp.296-301 |
Publisher: | IEEE |
Publisher Place: | USA |
Issue Date: | 2005 |
Series/Report no.: | IEEE Conference on Computer Vision and Pattern Recognition |
ISBN: | 0769523722 9780769523729 |
ISSN: | 1063-6919 |
Conference Name: | IEEE Computer Society Conference on Computer Vision and Pattern Recognition (18th : 2005 : San Diego, CA, U.S.A.) |
Editor: | Schmid, C. Soatto, S. Tomasi, C. |
Statement of Responsibility: | Gustavo Carneiro, Allan D. Jepson |
Abstract: | We introduce a new method that characterizes typical local image features (e.g., SIFT, phase feature) in terms of their distinctiveness, detectability, and robustness to image deformations. This is useful for the task of classifying local image features in terms of those three properties. The importance of this classification process for a recognition system using local features is as follows: a) reduce the recognition time due to a smaller number of features present in the test image and in the database of model features; b) improve the recognition accuracy since only the most useful features for the recognition task are kept in the model database; and c) increase the scalability of the recognition system given the smaller number of features per model. A discriminant classifier is trained to select well behaved feature points. A regression network is then trained to provide quantitative models of the detection distributions for each selected feature point. It is important to note that both the classifier and the regression network use image data alone as their input. Experimental results show that the use of these trained networks not only improves the performance of our recognition system, but it also significantly reduces the computation time for the recognition process. |
Rights: | Copyright © 2005 by The Institute of Electrical and Electronics Engineers, Inc. |
DOI: | 10.1109/CVPR.2005.340 |
Published version: | http://dx.doi.org/10.1109/cvpr.2005.340 |
Appears in Collections: | Aurora harvest Computer Science publications |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.