Content-Based Trademark Retrieval System Using Visually Salient Features

Abstract

An ever increasing number of registered trademarks has created greater demand for an automatic trademark retrieval system. We present a method for such a system based on the image content using shape features. Zernike or pseudo-Zernike moments of the image are employed as a feature set. To retrieve similar shapes, we take into account visually salient features that dominantly affect the global shape of the trademarks and ignore their minor detail. Experimental results on a database of 3,000 trademark images demonstrate that the proposed method retrieves visually similar trademarks which agree well with human perception.

Cite

Text

Kim and Kim. "Content-Based Trademark Retrieval System Using Visually Salient Features." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1997. doi:10.1109/CVPR.1997.609340

Markdown

[Kim and Kim. "Content-Based Trademark Retrieval System Using Visually Salient Features." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1997.](https://mlanthology.org/cvpr/1997/kim1997cvpr-content/) doi:10.1109/CVPR.1997.609340

BibTeX

@inproceedings{kim1997cvpr-content,
  title     = {{Content-Based Trademark Retrieval System Using Visually Salient Features}},
  author    = {Kim, Yong-Sung and Kim, Whoi-Yul},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1997},
  pages     = {307-312},
  doi       = {10.1109/CVPR.1997.609340},
  url       = {https://mlanthology.org/cvpr/1997/kim1997cvpr-content/}
}