Discovery of a perceptual distance function for measuring image similarity

Beitao Li, Edward Y. Chang, Yi-Leh WuMultim. Syst 2003 · OpenReview

Abstract

For more than a decade, researchers have actively explored the area of image/video analysis and retrieval. Yet one fundamental problem remains largely unsolved: how to measure perceptual similarity between two objects. For this purpose, most researchers employ a Minkowski-type metric. Unfortunately, the Minkowski metric does not reliably find similarities in objects that are obviously alike. Through mining a large set of visual data, our team has discovered a perceptual distance function. We call the discovered function the dynamic partial function (DPF). When we empirically compare DPF to Minkowski-type distance functions in image retrieval and in video shot-transition detection using our image features, DPF performs significantly better. The effectiveness of DPF can be explained by similarity theories in cognitive psychology.
BibTeX
@inproceedings{li2003discovery,
  author = {Beitao Li and Edward Y. Chang and Yi-Leh Wu},
  title = {{Discovery of a perceptual distance function for measuring image similarity}},
  booktitle = {Multim. Syst},
  year = {2003},
  url = {https://openreview.net/forum?id=-0cgcT1SqFKp},
}

Loading related content...

Figure