- Title
- A geometric method to compute directionality features for texture images
- Creator
- Islam, Md; Zhang, Dengsheng; Lu, Guojun
- Date
- 2008
- Type
- Text; Conference paper
- Identifier
- http://researchonline.federation.edu.au/vital/access/HandleResolver/1959.17/70788
- Identifier
- vital:6576
- Identifier
-
https://doi.org/10.1109/ICME.2008.4607736
- Identifier
- ISBN:9781424425716
- Abstract
- In content based image analysis and retrieval, texture feature is an essential component due to its strong discriminative power. Directionality is one of the most significant texture features which are well perceived by the human visual system. A new method to calculate the directionality of image is proposed in this paper. In contrast to Tamura method which uses the statistical property of the directional histogram of an image to calculate its directionality, the proposed method makes use of the geometric property of the directional histogram. Both subjective and objective analyses prove that the proposed method outperforms the conventional Tamura method. It has also been shown that the proposed directionality has better retrieval performance than the conventional Tamura directionality.
- Publisher
- Hannover IEEE
- Relation
- Proceedings of the 2008 IEEE International Conference on Multimedia and Expo p. 1521-1524
- Rights
- This metadata is freely available under a CCO license
- Subject
- Feature extraction; Image retrieval; 0801 Artificial Intelligence and Image Processing
- Reviewed
- Hits: 1365
- Visitors: 1341
- Downloads: 0