Developing RDF-based Semantic Annotations for Image Resources Management

• Main Authors: Yu-Ching Hsu, 徐禹晴
• Other Authors: Yu-Liang Chi
• Format: Others
• Language: zh-TW
• Published: 2006
• Online Access: http://ndltd.ncl.edu.tw/handle/77603537019779422225

碩士 === 中原大學 === 資訊管理研究所 === 94 === At the present day, the technology of in the field of digital media generates huge amounts of non-textual information such as images. The potential for exchange and retrieval is vast and daunting. This type of information needs to add textual descriptions to promote information retrieval. Traditional information retrieval used a keyword-based or full-text search engine to extract useful information of textual contents. And what is more employs to exploring non-textual information by creating metadata models and annotations, but it still stay on data level. Words may not appropriate representations for their meanings and retrieve all the relevant information. Due to these annotations without ability of knowledge representation, cause it not much more to help users find the desired information. Most of ontology developers adopt export’s knowledge and experience. When users lose cognitive ability about background of domain, even database have lots of multimedia data but always find out. Because the gap between users and information retrieval. Therefore this paper imports method from Semantic Difference (SD) of Kansei Engineering to develop a consumer-orientated ontology that applies to semantic annotation and retrieval for images. In addition, we improve annotation of images by knowledge way that utilizes Resource Description Framework (RDF) for describing information object, and promote to semantic level. Finally, we employ vascular plant images and related digital archives as test samples for our annotation model from the national museum of nature science (NMNS). We acquire descriptive cognition about vascular plants on surface by users, for the purpose of developing consumer-orientated ontology. To create knowledge-based annotation model, and provides semantic retrieval for users by their cognition. This paper presents a guidance that can be facilitated to manage image resources in a knowledge way.