ML Anthology

Enhancing DPF for Near-Replica Image Recognition

Yan Meng, Edward Y. Chang, Beitao Li
CVPR 2003 pp. 416-423
doi:10.1109/CVPR.2003.1211498 /cvpr/2003/meng2003cvpr-enhancing/

Abstract

Dynamic Partial Function (DPF), which dynamically selects a subset of features to measure pairwise image similarity, has been shown to be very effective in near-replica image recognition. DPF, however, suffers from the one-size-fits-all problem: it requires that all pairwise similarity measurements must use the same number of features. We propose methods for enhancing DPF's performance by allowing different numbers of features to be selected in a pairwise manner. Through extensive empirical studies, we show that our three schemes: thresholding, sampling and weighting, and hybrid schemes of these three basic approaches, substantially outperform DPF in near-replica image recognition.

CVPR Semantic Scholar

Cite

Text

Meng et al. "Enhancing DPF for Near-Replica Image Recognition." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2003. doi:10.1109/CVPR.2003.1211498

Markdown

[Meng et al. "Enhancing DPF for Near-Replica Image Recognition." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2003.](https://mlanthology.org/cvpr/2003/meng2003cvpr-enhancing/) doi:10.1109/CVPR.2003.1211498

BibTeX

@inproceedings{meng2003cvpr-enhancing,
  title     = {{Enhancing DPF for Near-Replica Image Recognition}},
  author    = {Meng, Yan and Chang, Edward Y. and Li, Beitao},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2003},
  pages     = {416-423},
  doi       = {10.1109/CVPR.2003.1211498},
  url       = {https://mlanthology.org/cvpr/2003/meng2003cvpr-enhancing/}
}