Zhao, Zhijie and Gao, Ze and Sun, Huadong and Jin, Xuesong (2019) Research on Fourier Descriptor Image Retrieval Technology Based on Minimum Inertia Axis. In: Wireless and Satellite Systems. 10th EAI International Conference, WiSATS 2019, Harbin, China, January 12–13, 2019, Proceedings, Part I.
31598.pdf
Download (811kB)
Abstract
In image retrieval, the shape feature is one of the key features of image content description. At present, most of the widely used Fourier descriptors in shape descriptors are invariant in translation, rotation and scale expansion. But Fourier descriptors are susceptible to the location of the starting point. In this paper, an improved image retrieval method based on Fourier descriptors is proposed. First, the image is preprocessed and the edge of the image is extracted. Secondly, the starting point of the contour is determined by the minimum inertia axis. Then Fourier transform is used to get eigenvectors. Finally, the correlation coefficient is used to calculate the similarity. Experiments show that the Fourier Descriptor Image Retrieval Method based on the minimum inertia axis is more efficient than other methods in Swedish Leaf database.
| Item Type: | Conference or Workshop Item (UNSPECIFIED) |
|---|---|
| Date Deposited: | 04 Mar 2026 12:02 |
| Last Modified: | 20 Nov 2026 13:30 |
| URI: | https://eprints.eai.eu/id/eprint/22408 |
