Comparison of local feature descriptors for mobile visual search

13 years 2 months ago

Download www.stanford.edu

We evaluate the performance of MPEG-7 image signatures, Compressed Histogram of Gradients descriptor (CHoG) and Scale Invariant Feature Transform (SIFT) descriptors for mobile visual search applications. We observe that SIFT and CHoG outperform MPEG-7 image signatures greatly in terms of feature-level Receiver Operating Characteristic (ROC) performance and imagelevel matching. Moreover, CHoG descriptors demonstrate such gains while being comparable with MPEG-7 image signatures in bit-rate.

Vijay Chandrasekhar, David M. Chen, Andy Lin, Gabr

Real-time Traffic

ICIP 2010 | Image Processing | Invariant Feature Transform | MPEG-7 | Signatures |

claim paper

» SURFTrac Efficient Tracking and Continuous Object Recognition using Local Feature Descript...

» CHoG Compressed histogram of gradients A low bitrate feature descriptor

» A setup for evaluating detectors and descriptors for visual tracking

» Histogram of Oriented Cameras A New Descriptor for Visual SLAM in Dynamic Environments

» Feature Based Condensation for Mobile Robot Localization

» Visual Localization Using Global Visual Features and Vanishing Points

» Computers and iphones and mobile phones oh my a logsbased comparison of search users on di...

» Cascade of descriptors to detect and track objects across any network of cameras

Post Info
More Details (n/a)

Added	12 Feb 2011
Updated	12 Feb 2011
Type	Journal
Year	2010
Where	ICIP
Authors	Vijay Chandrasekhar, David M. Chen, Andy Lin, Gabriel Takacs, Sam S. Tsai, Ngai-Man Cheung, Yuriy A. Reznik, Radek Grzeszczuk, Bernd Girod

Comments (0)

Sciweavers

Comparison of local feature descriptors for mobile visual search

ICIP 2010 | Image Processing | Invariant Feature Transform | MPEG-7 | Signatures |

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers