期刊
JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY
卷 93, 期 2-3, 页码 139-146出版社
SPRINGER
DOI: 10.1007/s11265-019-01508-y
关键词
Image retrieval; Shape features; Color features
资金
- National Natural Science Foundation of China [61972136, 61471161, 61971339]
- Hubei Provincial Department of Education Outstanding Youth Scientific Innovation Team Support Foundation [T201410]
- Hubei Province Higher Education Teaching Research Project [2018432]
This paper proposes an image retrieval algorithm based on the combination of color and shape features, which effectively improves the accuracy of image retrieval as verified by experiments.
With the development of content-based image retrieval technology, the retrieval efficiency of image retrieval technology is getting higher and higher. For different data images, image retrieval based on color features and shape features can be used to improve retrieval efficiency. However, when a single image feature is retrieved, its retrieval efficiency still cannot meet people's needs. In this paper, we propose an image retrieval algorithm based on the combination of color and shape features. The cumulative histogram method is used to calculate the color features of the image, and 7 Hu invariant moments are calculated as shape features. The color and shape features are combined with certain weights, and the Euclidean distance is used as the similarity measure. Finally, the image is retrieved, and the related experiments are passed. By comparing with related experiments, the algorithm effectively improves the accuracy of image retrieval.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据