Scalable Object Discovery: A Hash-Based Approach to Clustering Co-occurring Visual Words

@article{Pineda2011ScalableOD,
  title={Scalable Object Discovery: A Hash-Based Approach to Clustering Co-occurring Visual Words},
  author={Gibran Fuentes Pineda and Hisashi Koga and Toshinori Watanabe},
  journal={IEICE Transactions},
  year={2011},
  volume={94-D},
  pages={2024-2035}
}
We present a scalable approach to automatically discovering particular objects (as opposed to object categories) from a set of images. The basic idea is to search for local image features that consistently appear in the same images under the assumption that such co-occurring features underlie the same object. We first represent each image in the set as a set of visual words (vector quantized local image features) and construct an inverted file to memorize the set of images in which each visual… CONTINUE READING

References

Publications referenced by this paper.
Showing 1-10 of 26 references

Similar Papers

Loading similar papers…