Robust order-based methods for feature description
- 1 January 2010
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
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-of-gradients 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 strengths and that by combining the two descriptors, one obtains much better results than either of them considered separately. The results are shown on the standard 2D Oxford and the 3D Caltech datasets.Keywords
This publication has 21 references indexed in Scilit:
- Improving Descriptors for Fast Tree Matching by Optimal Linear ProjectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- Evaluation of Features Detectors and Descriptors based on 3D ObjectsInternational Journal of Computer Vision, 2006
- An Intensity-augmented Ordinal Measure for Visual CorrespondencePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Efficient shape matching using shape contextsIeee Transactions On Pattern Analysis and Machine Intelligence, 2005
- A performance evaluation of local descriptorsIeee Transactions On Pattern Analysis and Machine Intelligence, 2005
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- Scale & Affine Invariant Interest Point DetectorsInternational Journal of Computer Vision, 2004
- Multiresolution gray-scale and rotation invariant texture classification with local binary patternsIeee Transactions On Pattern Analysis and Machine Intelligence, 2002
- Non-parametric local transforms for computing visual correspondenceLecture Notes in Computer Science, 1994
- A Combined Corner and Edge DetectorPublished by British Machine Vision Association and Society for Pattern Recognition ,1988