Small Codes and Large Image Databases for Recognition

Rob Fergus
New York University

The Internet contains billions of images, freely available online. Methods for ef?ciently searching this incredibly rich resource are vital for a large number of applications. These include object recognition, computer graphics, personal photo collections, online image search tools.
In this talk we describe ef?cient 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.

Joint work with A. Torralba and Y. Weiss.

Back to Large Scale Multimedia Search