臺灣博碩士論文加值系統

本研究探討如何發展以本體技術為核心的註記機制，應用於圖像資源的管理，在發展知識架構時，納入使用者的認知問題作為本體設計的考量，縮短其與資訊檢索間的落差。有鑑於非文字性資料(如圖像資料)，因本身不具文字特性，需藉由外部的描述機制，使其具有類似文字性資料的特性可供檢索，以協助資訊檢索系統的運作，然而現階段的註記，由於僅概略地針對資料作說明，且較不具知識表達的能力，而仍處於資料的層級。在註記的框架及內容方面，則多是以該領域專家的知識及經驗為主，若使用者對該領域的認知不足，易造成使用者在檢索上的障礙，故本研究引用感性工學(Kansei Engineering)中語意差異法(Semantic Difference)的概念，擷取出使用者對查詢標的物的認知，發展使用者導向的本體，應用於圖像的註記及檢索上，並採用資源描述架構(Resource Description Framework)做為資訊物件的描述格式，RDF為本體語言之一，用以改良詮釋資料的定義方式，協助提供知識表達型的圖像註記，並改善現有圖像的註記機制，使註記的資料格式由單純的資料層級，提升為具知識表達能力的語意層級。本研究最後以國立自然科學博物館的「維管束植物圖片」為例，擷取一般大眾對植物外觀描述上的認知，發展植物註記本體，並建立「知識化圖像註記模型」，提供使用者以「認知」為導向的語意檢索方式，作為有價值的實證應用。

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.

摘要 I
英文摘要 II
誌謝辭 III
目　　錄 IV
圖 目 錄 VI
表 目 錄 VII
第一章　緒論 1
1.1 研究背景及動機 1
1.2 研究問題 2
1.3 研究目的 4
第二章　文獻探討 6
2.1 知識表達(KNOWLEDGE REPRESENTATION) 6
2.1.1 以概念為基礎的知識表達方式 7
2.1.2本體表達語言 9
2.1.3資源描述架構(RESOURCE DESCRIPTION FRAMEWORK) 10
2.2註記 13
2.2.1 一般描述型註記 14
2.2.2 知識表達型註記 15
2.3 圖像檢索 16
2.3.1以關鍵字為基礎 16
2.3.2以樣本為基礎 17
2.3.3以語意為基礎 17
第三章 研究設計 19
3.1 系統設計 19
3.2 知識化註記模型 20
3.3 語意檢索方式 26
第四章 系統實作 29
4.1 問卷設計 29
4.2 建置使用者導向之註記本體 34
4.3 本體編輯及實作 41
4.4 以本體表達知識註記 44
4.5 查詢引擎 47
4.6 檢索情境 49
第五章 分析與討論 52
第六章 結論 54
6.1 研究結論 54
6.2 研究貢獻 55
6.3 未來研究建議 56
參考文獻 57

圖 目 錄
圖1-1 資料類型與對應的資料檢索...........................................................................1
圖1-2 使用者認知與領域專家知識的鴻溝...............................................................3
圖1-3 使用者導向的註記方式...................................................................................4
圖2-1 多媒體註記的層級.........................................................................................11
圖2-2 資料層級的註記.............................................................................................14
圖2-3 語意層級的註記.............................................................................................16
圖3-1 系統架構圖.....................................................................................................20
圖3-2 知識化註記模型.............................................................................................21
圖3-3 本體建置程序圖.............................................................................................23
圖3-4 知識註記的形成.............................................................................................26
圖3-5 語意檢索方式.................................................................................................27
圖3-6 本體部份架構之推理關係圖.........................................................................28
圖4-1 問卷設計.........................................................................................................30
圖4-2 萃取出的代表性詞彙( 43對).........................................................................32
圖4-3 未萃取的形容詞詞彙( 41對).........................................................................33
圖4-4 註記本體架構.................................................................................................41
圖4-5 使用PROTÉGÉ建構本體的類別(CLASS)及屬性(SLOT)...........................42
圖4-6 定義屬性的範圍及限制.................................................................................42
圖4-7 註記本體的RDF SCHEMA檔........................................................................44
圖4-8 花的註記實例.................................................................................................44
圖4-9 樹木註記的實例.............................................................................................45
圖4-10 已註記的RDF檔...........................................................................................46
圖4-11 SPARQL查詢方式.........................................................................................47
圖4-12 RDF推理的例子............................................................................................49
圖4-13 檢索情境.......................................................................................................49
圖4-14 檢索系統介面...............................................................................................50
圖4-15 SPARQL查詢.................................................................................................51
圖4-16 檢索結果.......................................................................................................51

表 目 錄
表2-1 知識表達的四種形式.......................................................................................7
表2-2 本體定義...........................................................................................................7
表2-3 本體方法相關規範...........................................................................................9
表2-4 註記的目的.....................................................................................................13
表2-5 以多媒體為主的後設資料標準簡介.............................................................15
表4-1 本研究之本體的領域與範圍.........................................................................34
表4-2 DUBLIN CORE元素集................................................................................35
表4-3 具體植物子類別的定義.................................................................................36
表4-4 整體的描述詞彙列表.....................................................................................37
表4-5 花的描述詞彙列表.........................................................................................37
表4-6 果的描述詞彙列表.........................................................................................38
表4-7 葉的描述詞彙列表.........................................................................................38
表4-8 屬性限制.........................................................................................................39
表4-9 註記資料的格式.............................................................................................40
表5-1 註記的比較.....................................................................................................53
表5-2 檢索的比較.....................................................................................................53

[中文部份]
[1]自然科學博物館，「知識單元-植物」2005, Online Available at: http://ndap.nmns.edu.tw/
[2]行政院農業委員會，「臺灣維管束植物簡誌」1997, Online Available at: http://preserve.coa.gov.tw/species/vascular/index.htm
[3]林崇宏，設計原理，台北：全華科技圖書股份有限公司，1998。
[4]後設資料工作組，「參考規範-後設資料標準簡介」2005, Online Available at: http://www.sinica.edu.tw/~metadata/standard/standardCP.html
[5]戚玉樑，「以本體技術為基礎的知識庫建置程序及其應用」，資訊科技與社會，第5卷第2期，2005，pp. 1-18.
[6]戚玉樑，「協同知識擷取與知識表達程序於建構本體的概念架構」，資訊管理學報，2006，(In press)
[7]黃增泉，植物分類學：臺灣維管束植物科誌，台北：南天出版社印行，1993。
[8]繽紛旅遊網，「認識植物的分類」2002, Online Available at: http://www.befuntravel.com.tw/discuss/picdiscuss/plant.asp

[英文部份]
[1]Alani, H., Kim, S., Millard, D.E., Weal, M.J., Hall, W., Lewis, P.H., and Shadbolt, N.R., “Automatic Ontology-based Knowledge Extraction from Web Documents,” IEEE Intelligent Systems, Vol. 18, No. 1, 2003, pp. 14-21.
[2]Anderson, Lee K., Taylor, James R., and Holloway, Robert J., “The Consumer and His Alternatives: An Experimental Approach,” Journal of Marketing Research, Vol. 3, No. 2, 1966, pp. 62-67.
[3]Berner-Lee, T., Handler, J., and Lassila, O., The Semantic Web, Scientific America, 2001.
[4]Bertino, E., Catania, B., and Zarri, G. P., “A Conceptual Annotation Approach to Indexing In a Web-Based Information System,” Economic Research and Electronic Networking Journal (NETNOMICS), Vol.2, No. 3, 2000, pp.160-165.
[5]Bimbo, A. D., Pala, P., “Visual Image Retrieval by Elastic Matching of User Sketches,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 19, No. 2, 1997, pp. 121-132.
[6]BioOntology Core Group, “XOL Ontology Exchange Language,” 1999, Online Available at: http://www.ai.sri.com/~pkarp/xol/
[7]Broekstra, J., Klein, M., Decker, S., Fensel, D., Harmelen, F., and Horrocks, I., “Enabling Knowledge Representation on the Web by Extending RDF Schema,” Computer Networks, Vol. 39, No. 5, 2002, pp. 609-634.
[8]Chandrasekaran, B., Josephson, J. R., and Benjamins, R., “What Are Ontologies, and Why Do We Need Them,” IEEE Intelligent Systems, Vol. 14, No. 1, 1999, pp. 20-26.
[9]DARPA's Information Exploitation Office, “Darpa Agent Markup Language and Ontology Interchange Language,” 2000, Online Available at: http://www.daml.org/
[10]Denoue, L., and Vignollet, L., “An Annotation Tool for Web Browsers and Its Applications to Information Retrieval,” In Proceedings of RIAO2000, 2000.
[11]Euzenat, J., “Eight Questions about Semantic Web Annotations,” IEEE Intelligent Systems, Vol.17, No. 2, 2002, pp. 55-62.
[12]Gazzale, Robert S., and MacKie-Mason, Jeffrey K., “Endogenous Differentiation of Information Goods under Uncertainty,” ACM Electronic Commerce, 2001.
[13]Geurts, J., Ossenbruggen, J., and Hardman, L., “Requirements for Practical Multimedia Annotation,” In Workshop on Multimedia and the Semantic Web, 2005, pp. 4-11.
[14]Gomez-Perez, A., and Corcho, O., “Ontology Languages for the Semantic Web,” IEEE Intelligent Systems, Vol. 17, No. 1, 2002, pp. 54-60.
[15]Gomez-Perez, A., Fernandez-Lopez, M., and Corcho-Garcia, O., “Ontological Engineering: with Examples from the Areas of Knowledge Management, E-commerce and the Semantic Web,” Springer Verlag, 2004.
[16]Gruber, T. R., “A Translation Approach to Portable Ontology Specification,” Knowledge Acquisition, Vol. 5, No. 2, 1993, pp. 199-220.
[17]Gruber, T. R., “Towards Principles for The Design of Ontologies Used for Knowledge Sharing,” International Journal of Human-Computer Studies, Vol. 43, No. 5-6, 1995, pp. 907-928.
[18]Guarino, N., “Formal Ontology in Information Systems,” In Proceedings of FOIS’98, 1998, pp. 3-15.
[19]Hjelm, J., Creating the Semantic Web with RDF, John Wiley & Sons, NY: New York, 2001.
[20]Horrocks, I., Patel-Schneider, P.F., and Harmelen, F.V., “From SHIQ and RDF to OWL: the making of a Web Ontology Language,” Journal of Web Semantics, Vol. 1, No. 1, 2003, pp. 7-26.
[21]HP Labs, “ARQ - A SPARQL Processor for Jena,” 2006, Online Available at: http://jena.sourceforge.net/ARQ/
[22]HyvÄonen, E., Styrman, A., and Saarela, S., “Ontology-Based Image Retrieval,” In Helsinki Institute for Information Technology (HIIT) Publications, Budapest, 2003, pp. 15-27.
[23]Hunter, J., Armstrong, L., “A Comparison of Schemas for Video Metadata Representation,” In Proceedings of the WWW8, 1999, pp. 10-14.
[24]Jenkins, C., Jackson, M., Burden, P., and Wallis, J., “Automatic RDF Metadata Generation for Resource Discovery,” Computer Networks, Vol. 31, No. 15, 1999, pp. 11-16.
[25]Karvounarakis, G., Alexaki, S., Christofides, V., Plexousakis, D., and Scholl, M., “RQL: A Declarative Query Language for RDF,” In Proceedings of the 11th international conference on World Wide Web (WWW'02), Honolulu, Hawaii, USA, 2002.
[26]Khan, Latifur, McLeod, Dennis, and Hovy, Eduard, “Retrieval Effectiveness of an Ontology-based Model for Information Selection,” The International Journal on Very Large Databases, Vol. 13, No. 1, 2004, pp.71–85.
[27]Kiryakov, A., Popov, B., Terziev, I., Manov, D., and Ognyanoff, D., “Semantic Annotation, Indexing, and Retrieval,” Journal of Web Semantics, Vol. 2, No. 1, 2004, pp. 49-79.
[28]Klatzky, R. L., Human Memory: Structures and Processes, W. H. Freeman and Company, 1975.
[29]Klein, M., “XML, RDF, and Relatives,” IEEE Intelligent Systems, Vol. 16, No. 2, 2001, pp. 26-28.
[30]Klyne, G., and Carroll, J. J., “Resource Description Framework (RDF) Concepts and Abstract Syntax, ” 2004, Online Available at: http://www.w3.org/TR/rdf-concepts/
[31]Ko, ByoungChul, and Byun, Hyeran, “Multiple Regions and Their Spatial Relationship-Based Image Retrieval,” Image And Video Retrieval Lecture Notes In Computer Science, 2002, pp. 81-90.
[32]López de Vergara, J.E., Villagrá, V.A., and Berrocal, J., “Applying the Web Ontology Language to Management Information Definitions,” IEEE Communication magazine, Vol. 42, No. 7, 2004, pp. 68-74.
[33]Maedche, A., Neumann, G., and Staab, S., “Bootstrapping an Ontology-based Information Extraction System,” Studies In Fuzziness and Soft Computing, 2002.
[34]Marshall, C. C., Price, M. N., Golovchinsky, G., and Schilit, B. N., “Designing E-books for Legal Work,” In Proceedings of Joint Conference on Digital Libraries(JCDL), 2001, pp.41-48.
[35]McBride, B., “The Resource Description Framework (Resource Description Framework) and its Vocabulary Description Language RDFS,” Handbook on Ontologies, Springer-Verlag, 2004, pp. 51-65.
[36]Nagao, K., Shirai, Y., and Squire, K., “Semantic Annotation and Transcoding: Making Web Content More Accessible,” IEEE MultiMedia, Vol. 8, No. 2, 2001, pp. 69-81.
[37]Neches, R., Fikes, R., Finin, T., Gruber, T., Patil, R., Senator, T., and Swartout, W. R., “Enabling Technology for Knowledge Sharing,” AI Magazine, Vol. 12, No. 3, 1991, pp. 36-56.
[38]Noy, N.F., Sintek, M., Decker, S., Crubezy, M., Fergerson, R.W., and Musen, M.A., “Creating Semantic Web contents with Protege-2000,” IEEE Intelligent Systems, Vol. 16, No. 2, 2001, pp. 60–71.
[39]Parallel Understanding Systems Group, “Simple HTML Ontology Extensions,” 2003, Online Available at: http://www.cs.umd.edu/projects/plus/SHOE/
[40]Phelps, T. A., and Wilensky, R., “Multivalent Annotations,” In Proceedings of the First European Conference on Research and Advanced Technology for Digital Libraries, 1997, pp. 287-303.
[41]Rich, E., and Knight, K., Artificial Intelligence, McGraw-Hill, NY: New York, 1991.
[42]Schreiber, T., Dubbeldam, B., Wielemaker, J., and Wielinga, B. J. ,“Ontology-based photo annotation,” IEEE Intelligent Systems, Vol. 16, No. 3, 2001, pp. 66-74.
[43]Soo, Von-Wun, Lee, Chen-Yu, Yeh, Jaw Jium, and Chen, Ching-chih, “Using Sharable Ontology to Retrieve Historical Images,” In Proceedings of the second ACM/IEEE-CS Joint Conference on Digital Libraries(JCDL’02), Portland, Oregon, USA, 2002, pp. 197-198.
[44]Stamou, G., Ossenbruggen, J., Pan, J. Z., and Schreiber, G., “Multimedia Annotations on the Semantic Web,” IEEE Multimedia, Vol. 13, No. 1, 2006, pp. 86-90.
[45]Stanford Medical Informatics, “Welcome to Protégé, ” 2006, Online Available at: http://protege.stanford.edu
[46]Tiun, S., Abdullah, R., and Kong, T. E., “Automatic Topic Identification Using Ontology Hierarchy,” In Proceedings of the Second International Conference on Computational Linguistics and Intelligent Text Processing, 2001, pp. 444-453.
[47]Ullman, S., “Visual Routines,” Cognition, Vol. 18, No. 1-3, 1984, pp. 97-159.
[48]Uschold, M., and Grueninger, M., “Ontologies: Principles, Methods and Applications,” Knowledge Engineering Review, Vol. 11, No. 2, 1996, pp. 93-155.
[49]Vaughan, L., “New Measurements for Search Engine Evaluation Proposed and Tested,” Information processing and Management, Vol. 40, No. 4, 2004, pp. 677-691.
[50]W3C Recommendation, “Ontology Web Language,” 2004, Online Available at: http://www.w3.org/2004/OWL/
[51]W3C Recommendation, “Resource Description Framework, ” 1999, Online Available at: http://www.w3.org/RDF/
[52]W3C Recommendation, “SPARQL Query Language for RDF, ” 2006, Online Available at: http://www.w3.org/TR/rdf-sparql-query/
[53]W3C, “Tutorial on Semantic Web Technologies,” 2006, Online Available at: http://www.w3.org/Consortium/Offices/Presentations/RDFTutorial/
[54]Wilensky, R., “Digital Library Resources as a Basis for Collaborative Work,” Journal of the American Society for Information Science, Vol. 51, No. 3, 2000, pp. 228-245.
[55]Witkin, H., and Goodenough, D., “Cognitive Styles: Essence and Origins: Field Dependence and Field Independence,” Psychological Issues, Vol. 14, No. 51, 1981, pp. 38-47.