Cultural advice

The Australian National University acknowledges, celebrates and pays our respects to the Ngunnawal and Ngambri people of the Canberra region and to all First Nations Australians on whose traditional lands we meet and work, and whose cultures are among the oldest continuing cultures in human history.

Aboriginal and Torres Strait Islander peoples are advised that ANU Library collections may include images, names, voices, and other representations of deceased persons.

Material in the collection may contain terms, language or views that reflect the period in which the item was created and may be considered inappropriate today.

A Fast Algorithm for Creating a Compact and Discriminative Visual Codebook

Date

Authors

Wang, Lei

Zhou, Luping

Shen, Chunhua

Publisher

Springer

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

Keywords

Keywords: Computer vision; Image processing; Object recognition; Classification performances; Codebook; Experimental studies; Fast algorithms; Memory costs; Object classes; Visual words; Powders

URI

http://hdl.handle.net/1885/36588

Collections

ANU Research Publications

Source

Proceedings of European Conference on Computer Vision (ECCV 2008)

Type

Conference paper

DOI

10.1007/978-3-540-88693-8-53

Restricted until

2037-12-31

Downloads

File

Description

01_Wang_A_Fast_Algorithm_for_Creating_2008.pdf (2.7 MB)