Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/67359
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Conference paper |
Title: | A fast algorithm for creating a compact and discriminative visual codebook |
Author: | Wang, L. Zhou, L. Shen, C. |
Citation: | Proceedings of 10th European Conference on Computer Vision (ECCV), 12-18 October, 2008 / D. Forsyth, P. Torr and A. Zisserman (eds.); Part IV, pp.719-732 |
Publisher: | Springer |
Publisher Place: | New York |
Issue Date: | 2008 |
Series/Report no.: | Lecture Notes in Computer Science; Vol. 5305 |
ISBN: | 3540886923 9783540886921 |
ISSN: | 0302-9743 1611-3349 |
Conference Name: | European Conference on Computer Vision (ECCV) (10th : 2008 : Marseille, France) |
Statement of Responsibility: | Lei Wang, Luping Zhou and Chunhua Shen |
Abstract: | In patch-based object recognition, using a compact visual codebook can boost computational efficiency and reduce memory cost. Nevertheless, compared with a large-sized codebook, it also risks the loss of discriminative power. Moreover, creating a compact visual codebook can be very time-consuming, especially when the number of initial visual words is large. In this paper, to minimize its loss of discriminative power, we propose an approach to build a compact visual codebook by maximally preserving the separability of the object classes. Furthermore, a fast algorithm is designed to accomplish this task effortlessly, which can hierarchically merge 10,000 visual words down to 2 in ninety seconds. Experimental study shows that the compact visual codebook created in this way can achieve excellent classification performance even after a considerable reduction in size. © 2008 Springer Berlin Heidelberg. |
Rights: | © Springer, Part of Springer Science+Business Media |
DOI: | 10.1007/978-3-540-88693-8_53 |
Published version: | http://dx.doi.org/10.1007/978-3-540-88693-8_53 |
Appears in Collections: | Aurora harvest 5 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.