An Interactive Annotation Framework for Image Retrieval

• Item type: SIG Technical Reports(1)
• 公開日: 2004-07-14
• タイトル: An Interactive Annotation Framework for Image Retrieval
• タイトル / 言語: en
• タイトル: An Interactive Annotation Framework for Image Retrieval
• 言語: eng
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_18gh
• 資源タイプ: technical report
• 著者所属: University of Nantes Polytechnic School/Tokyo Metropolitan University Graduate School of Engineering
• 著者所属: University of Nantes Polytechnic School
• 著者所属: Tokyo Metropolitan University Graduate School of Engineering
• 著者所属: Tokyo Metropolitan University Graduate School of Engineering
• 著者所属: Tokyo Metropolitan University Graduate School of Engineering
• 著者所属(英): en
• 著者所属(英): University of Nantes, Polytechnic School/Tokyo Metropolitan University, Graduate School of Engineering
• 著者所属(英): en
• 著者所属(英): University of Nantes, Polytechnic School
• 著者所属(英): en
• 著者所属(英): Tokyo Metropolitan University, Graduate School of Engineering
• 著者所属(英): en
• 著者所属(英): Tokyo Metropolitan University, Graduate School of Engineering
• 著者所属(英): en
• 著者所属(英): Tokyo Metropolitan University, Graduate School of Engineering
• 著者名: Kaoru, KATAYAMA
• 著者名(英): Kaoru, Katayama
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: Image retrieval is usually based on content information external annotation or a combination of the two. While content information is intrinsic to the image and thus is an objective data external annotation may imply human and be deeply dependent on the culture and sensibility of the annotator. Consequently two operators would not produce the same annotation for the same image and both results may not be satisfying for user. However an image usually contain important information impossible to retrieve from content thus relying only on content information does not produce satisfying results. To answer to this issue we propose an annotation framework featuring an explicit separation of objective and subjective informations objective informations including content based information and a limited number of annotations the other annotations being considered as subjective information and collected with the help of the user. We also propose an efficient way to apply these subjective annotations to a navigation structure calculated before-hand from the objective informations. The resulting browsing technique brings the relevance of human annotation without the cost of a before-hand annotation and without denying the robustness of a before-hand calculated structure.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: Image retrieval is usually based on content information, external annotation, or a combination of the two. While content information is intrinsic to the image and thus is an objective data, external annotation may imply human and be deeply dependent on the culture and sensibility of the annotator. Consequently, two operators would not produce the same annotation for the same image, and both results may not be satisfying for user. However, an image usually contain important information impossible to retrieve from content, thus relying only on content information does not produce satisfying results. To answer to this issue, we propose an annotation framework featuring an explicit separation of objective and subjective informations, objective informations including content based information and a limited number of annotations, the other annotations being considered as subjective information and collected with the help of the user. We also propose an efficient way to apply these subjective annotations to a navigation structure calculated before-hand from the objective informations. The resulting browsing technique brings the relevance of human annotation without the cost of a before-hand annotation, and without denying the robustness of a before-hand calculated structure.
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AN10112482
• 書誌情報: 情報処理学会研究報告データベースシステム（DBS）; 巻 2004, 号 72(2004-DBS-134), p. 269-275, 発行日 2004-07-14
• Notice: SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc.
• 出版者 / 言語: ja
• 出版者: 情報処理学会