Incorporating Background Invariance into Feature-Based Object Recognition

Authors:
Andrew Stein;Martial Hebert
Affiliations:
Carnegie Mellon University, Pittsburgh, PA;Carnegie Mellon University, Pittsburgh, PA
Venue:
WACV-MOTION '05 Proceedings of the Seventh IEEE Workshops on Application of Computer Vision (WACV/MOTION'05) - Volume 1 - Volume 01
Year:
2005

Citing 0
Cited 7

Object recognition using a generalized robust invariant feature and Gestalt's law of proximity and similarity

Pattern Recognition
Occlusion Boundaries from Motion: Low-Level Detection and Mid-Level Reasoning

International Journal of Computer Vision
Local detection of occlusion boundaries in video

Image and Vision Computing
Bottom-up and top-down object matching using asynchronous agents and a contrario principles

ICVS'08 Proceedings of the 6th international conference on Computer vision systems
Scene interpretation: unified modeling of visual context by particle-based belief propagation in hierarchical graphical model

ACCV'06 Proceedings of the 7th Asian conference on Computer Vision - Volume Part II
Viewpoint induced deformation statistics and the design of viewpoint invariant features: singularities and occlusions

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part II
Genetic programming as strategy for learning image descriptor operators

Intelligent Data Analysis

Quantified Score

Hi-index	0.00

Visualization

Abstract

Current feature-based object recognition methods use information derived from local image patches. For robustness, features are engineered for invariance to various transformations, such as rotation, scaling, or affine warping. When patches overlap object boundaries, however, errors in both detection and matching will almost certainly occur due to inclusion of unwanted background pixels. This is common in real images, which often contain significant background clutter, objects which are not heavily textured, or objects which occupy a relatively small portion of the image. We suggest improvements to the popular Scale Invariant Feature Transform (SIFT) which incorporate local object boundary information. The resulting feature detection and descriptor creation processes are invariant to changes in background. We call this method the Background and Scale Invariant Feature Transform (BSIFT). We demonstrate BSIFT's superior performance in feature detection and matching on synthetic and natural images.