Multi-spectral SIFT for scene category recognition

Matthew A Brown, S Susstrunk

Research output: Chapter or section in a book/report/conference proceedingChapter in a published conference proceeding

359 Citations (SciVal)


We use a simple modification to a conventional SLR camera to capture images of several hundred scenes in colour (RGB) and near-infrared (NIR). We show that the addition of near-infrared information leads to significantly improved performance in a scene-recognition task, and that the improvements are greater still when an appropriate 4-dimensional colour representation is used. In particular we propose MSIFT – a multispectral SIFT descriptor that, when combined with a kernel based classifier, exceeds the performance of state-of-the-art scene recognition techniques (e.g., GIST) and their multispectral extensions. We extensively test our algorithms using a new dataset of several hundred RGB-NIR scene images, as well as benchmarking against Torralba’s scene categorization dataset.
Original languageEnglish
Title of host publication2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2011)
Number of pages8
ISBN (Print)9781457703942
Publication statusPublished - Jul 2011
EventIEEE Computer Vision and Pattern Recognition (CVPR) 2011 - Colorado Springs
Duration: 21 Jun 201125 Jun 2011


ConferenceIEEE Computer Vision and Pattern Recognition (CVPR) 2011
CityColorado Springs


Dive into the research topics of 'Multi-spectral SIFT for scene category recognition'. Together they form a unique fingerprint.

Cite this