A Convolutional Treelets Binary Feature Approach to Fast Keypoint Recognition

Abstract

Fast keypoint recognition is essential to many vision tasks. In contrast to the classification-based approaches [1,2], we directly formulate the keypoint recognition as an image patch retrieval problem, which enjoys the merit of finding the matched keypoint and its pose simultaneously. A novel convolutional treelets approach is proposed to effectively extract the binary features from the patches. A corresponding sub-signature-based locality sensitive hashing scheme is employed for the fast approximate nearest neighbor search in patch retrieval. Experiments on both synthetic data and real-world images have shown that our method performs better than state-of-the-art descriptor-based and classification-based approaches.

Cite

Text

Wu et al. "A Convolutional Treelets Binary Feature Approach to Fast Keypoint Recognition." European Conference on Computer Vision, 2012. doi:10.1007/978-3-642-33715-4_27

Markdown

[Wu et al. "A Convolutional Treelets Binary Feature Approach to Fast Keypoint Recognition." European Conference on Computer Vision, 2012.](https://mlanthology.org/eccv/2012/wu2012eccv-convolutional/) doi:10.1007/978-3-642-33715-4_27

BibTeX

@inproceedings{wu2012eccv-convolutional,
  title     = {{A Convolutional Treelets Binary Feature Approach to Fast Keypoint Recognition}},
  author    = {Wu, Chenxia and Zhu, Jianke and Zhang, Jiemi and Chen, Chun and Cai, Deng},
  booktitle = {European Conference on Computer Vision},
  year      = {2012},
  pages     = {368-382},
  doi       = {10.1007/978-3-642-33715-4_27},
  url       = {https://mlanthology.org/eccv/2012/wu2012eccv-convolutional/}
}