Fast and scalable keypoint recognition and image retrieval using binary codes

@article{Ventura2011FastAS,
  title={Fast and scalable keypoint recognition and image retrieval using binary codes},
  author={Jonathan Ventura and Tobias H{\"o}llerer},
  journal={2011 IEEE Workshop on Applications of Computer Vision (WACV)},
  year={2011},
  pages={697-702}
}
In this paper we report an evaluation of keypoint descriptor compression using as little as 16 bits to describe a single keypoint. We use spectral hashing to compress keypoint descriptors, and match them using the Hamming distance. By indexing the keypoints in a binary tree, we can quickly recognize keypoints with a very small database, and efficiently insert new keypoints. Our tests using image datasets with perspective distortion show the method to enable fast keypoint recognition and image… Expand
5 Citations

References

SHOWING 1-10 OF 20 REFERENCES
Survey of SIFT Compression Schemes
  • 48
  • PDF
Fast Keypoint Recognition in Ten Lines of Code
  • 503
  • PDF
BRIEF: Binary Robust Independent Elementary Features
  • 2,862
  • PDF
Small codes and large image databases for recognition
  • 791
  • PDF
Kernelized locality-sensitive hashing for scalable image search
  • B. Kulis, K. Grauman
  • Mathematics, Computer Science
  • 2009 IEEE 12th International Conference on Computer Vision
  • 2009
  • 839
  • PDF
Quantization schemes for low bitrate Compressed Histogram of Gradients descriptors
  • V. Chandrasekhar, Y. Reznik, +4 authors B. Girod
  • Mathematics, Computer Science
  • 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops
  • 2010
  • 29
  • Highly Influential
  • PDF
Scalable Recognition with a Vocabulary Tree
  • D. Nistér, Henrik Stewénius
  • Computer Science
  • 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)
  • 2006
  • 3,847
  • PDF
Robust feature matching in 2.3µs
  • 71
  • PDF
Speeded-Up Robust Features (SURF)
  • 10,762
  • PDF
Locality-sensitive binary codes from shift-invariant kernels
  • 637
  • PDF
...
1
2
...