| Paper: | MA-L6.1 |
| Session: | Image and Video Storage and Retrieval I |
| Time: | Monday, September 17, 09:50 - 10:10 |
| Presentation: |
Lecture
|
| Title: |
A NEW SHAPE SIGNATURE FOR FOURIER DESCRIPTORS |
| Authors: |
Akrem El-ghazal; University of Waterloo | | |
| | Otman Basir; University of Waterloo | | |
| | Saeid Belkasim; Georgia State University | | |
| Abstract: |
Shape-based image description is an important approach to Content-based Image Retrieval (CBIR). A variety of techniques are reported in the literature that aim to represent objects based on their shapes; each of these techniques has its advantages and disadvantages. Fourier Descriptor (FD), a simple yet powerful technique, has attractive properties such as rotational, scale, and translational invariance. In this paper we investigate this technique and present a novel shape registration method for extracting Fourier descriptors. When evaluated against Curvature Scale Space (CSS) and Zernike Moments (ZM) in shape-based image retrieval, the proposed technique exhibits superior performance. |
