TY - GEN
T1 - Small codes and large image databases for recognition
AU - Torralba, Antonio
AU - Fergus, Rob
AU - Weiss, Yair
PY - 2008
Y1 - 2008
N2 - 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 techniques 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.
AB - 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 techniques 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.
UR - http://www.scopus.com/inward/record.url?scp=51949119257&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2008.4587633
DO - 10.1109/CVPR.2008.4587633
M3 - Conference contribution
AN - SCOPUS:51949119257
SN - 9781424422432
T3 - 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR
BT - 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR
T2 - 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR
Y2 - 23 June 2008 through 28 June 2008
ER -