期刊
SYSTEMATICS AND BIODIVERSITY
卷 11, 期 1, 页码 19-33出版社
TAYLOR & FRANCIS LTD
DOI: 10.1080/14772000.2012.761655
关键词
biodiversity image retrieval; content-based image retrieval; image illustrations; monogenean; ontology
资金
- University of Malaya [PS284/2009B, RG053/09SUS]
In this paper, we propose a framework for Biodiversity Image Retrieval using Content Based Image Retrieval (CBIR) and structured vocabulary. The monogenean images used in this paper belong to the order Dactylogyridea Bychowsky, 1937. We use illustrations of monogenean haptoral bar diagnostic hard part to demonstrate how textual and content-based information can be integrated in building a better retrieval system. In this approach, an ontology-based image annotation and retrieval is developed to support the CBIR. Using ontology in combination with CBIR reduces the number of images needed in the training set, utilizing the provided user parameters. Efficiency of retrieval of the proposed approach is calculated using the relevance ranking and classification error rate of the retrieved images; and the efficiency of overall retrieval performance.
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