doi: 10.4304/jsw.9.4.931-937
An Effective Image Retrieval Method Based on Multi-features
- 1 School of Computer and Information Science, Southwest University, Chongqing, China
- 2 Department of Computing Science, Alberta University, Edmonton, Canada
Abstract
To improve the accuracy of image retrieval methods,an effective image retrieval method based on multifeaturesis proposed. The color feature of the image isextracted by constructing a (16:4:4) quantization schemeof image color. Perform the marked-watershed to achievethe segmentation of the image, and then extract Jan Flusserinvariant moments. Gaussian model is applied to normalizethe different subcharacters distance. The final multi-featuressimilarity consists of the color similarity and the shapesimilarity. Experiments demonstrate the efficiency of theproposed method.
Keywords
- image retrieval
- color feature
- shape fe
How to Cite
Lang Sun, Yan Tang, and Hong Zhang, "An Effective Image Retrieval Method Based on Multi-features," Journal of Software, vol. 9, no. 4, pp. 931-937, 2014. https://doi.org/ 10.4304/jsw.9.4.931-937
Copyright & License
Copyright © 2014 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).