barry:AREH

Barry Rafkind, Shih-Fu Chang. Angular Radial Edge Histogram. ADVENT Technical Report #218-2006-4 Columbia University, November 2006.

Download [help]

Download paper: Adobe portable document (pdf)

Copyright notice:This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

Abstract

The Angular Radial Edge Histogram (AREH) extends prior work on a compact image representation based on geometric distributions of edge pixels. Histograms of edge pixels are computed along the dimensions of angle and radius. Fourier transform is applied to accommodate rotation invariance. It achieves invariance for scale variation, in-plane rotation, and translation. By using a grid-based approach, it can also handle limited cases of partial occlusions. Our method is efficient . it does not require image segmentation or edge linking. We have evaluated its performance using an extensive set of test data including 12 different types of variations over diverse images (schematic diagrams and photos). Experimental results in image retrieval show that AREH outperforms baseline solutions using global edge direction histograms by a large margin

Contact

Barry Rafkind
Shih-Fu Chang

BibTex Reference

@TechReport{barry:AREH,
   Author = {Rafkind, Barry and Chang, Shih-Fu},
   Title = {Angular Radial Edge Histogram},
   Institution = {Columbia University},
   Month = {November},
   Year = {2006}
}

EndNote Reference [help]

Get EndNote Reference (.ref)

For problems or questions regarding this web site contact The Web Master.