Paper Info
Title
Small codes and large image databases for recognition
Abstract
The Internet contains billions of images, freely available online. Methods for efficiently searching this incredibly rich resource are vital for a large number of applications. These include object recognition (2), computer graphics (11, 27), personal photo collections, online image search tools. In this paper, our goal is to develop efficient image search and scene matching techniques that are not only fast, but also require very little memory, enabling their use on standard hardware or even on handheld devices. Our approach uses recently developed machine learning tech- niques to convert the Gist descriptor (a real valued vector that describes orientation energies at different scales and orientations within an image) to a compact binary code, with a few hundred bits per image. Using our scheme, it is possible to perform real-time searches with millions from the Internet using a single large PC and obtain recognition results comparable to the full descriptor. Using our codes on high quality labeled images from the LabelMe database gives surprisingly powerful recognition results using simple nearest neighbor techniques.
Year
DOI
Venue
2008
10.1109/CVPR.2008.4587633
Anchorage, AK
Keywords
DocType
ISSN
Internet,binary codes,image coding,image matching,image retrieval,learning (artificial intelligence),object recognition,search engines,very large databases,visual databases,Gist descriptor,Internet,compact binary code,image recognition,image search technique,large image database,machine learning,object recognition,scene matching technique
Conference
1063-6919 E-ISBN : 978-1-4244-2243-2
ISBN
Citations 
PageRank 
978-1-4244-2243-2
392
29.90
References 
Authors
23
3
Search Limit
100392
Name
Order
Citations
PageRank
Antonio Torralba114607956.27
Robert Fergus211214735.18
Yair Weiss310240834.60