Sciweavers

Share
CVPR
2010
IEEE

Robust Order-based Methods for Feature Description

11 years 7 months ago
Robust Order-based Methods for Feature Description
Feature-based methods have found increasing use in many applications such as object recognition, 3D reconstruction and mosaicing. In this paper, we focus on the problem of matching such features. While a histogram-ofgradients type methods such as SIFT, GLOH and Shape Context are currently popular, several papers have suggested using orders of pixels rather than raw intensities and shown improved results for some applications. The papers suggest two different techniques for doing so: (1) A Histogram of Relative Orders in the Patch and (2) A Histogram of LBP codes. While these methods have shown good performance, they neglect the fact that the orders can be quite noisy in the presence of Gaussian noise. In this paper, we propose changes to these approaches to make them robust to Gaussian noise. We also show how the descriptors can be matched using recently developed more advanced techniques to obtain better matching performance. Finally, we show that the two methods have complimentary s...
Raj Gupta, Anurag Mittal, Harshal Patil
Added 23 Jun 2010
Updated 23 Jun 2010
Type Conference
Year 2010
Where CVPR
Authors Raj Gupta, Anurag Mittal, Harshal Patil
Comments (0)
books