吳家麟臺灣大學：資訊網路與多媒體研究所劉治杰Liu, Chih-ChiehChih-ChiehLiu2007-11-272018-07-052007-11-272018-07-052006http://ntur.lib.ntu.edu.tw//handle/246246/58414因為數位相機的普及，人們在出外旅遊時，會大量的拍攝數位照片。然而之後的管理和整理確是件很麻煩的事情，要有效率地收尋、檢索或者再次瀏覽，都需要一套良好的管理系統。 在我們的論文中，便提出了一份根據旅遊計劃的協助下，所做的智慧型旅遊見聞管理系統。首先，利用收尋引擎獲取旅遊計劃裡提到的地名的圖片（以下稱為參考圖片），同時也對使用者所拍的照片作時間上的分群，接著計算參考圖片和照片群組之間的相似度，藉此判斷些照片是在哪些地點所拍攝的。 當知道照片所拍攝的位置後，一方面，我們可以對照片作簡單的標籤或註解。另一方面，我們可以結合其他媒體，例如地圖和文字，做富含地理資訊的展示、導覽。本論文中，提供了結合Google Map，Google Earth的圖片展示，和有關於台灣大學的導覽系統。An intelligent travel experience management system, abbreviated as ITEMS, is proposed to help tourists organize and present the digital travel contents in an automatic and efficient manner. Readily available metadata are adopted to reduce the overhead of user intervention and manual annotation. Robust image similarity metrics are also incorporated to utilize the power searching capability of WWW search engines. The proposed system automatically identifies the embedded geo-information of personal media, and accordingly integrates media with map and text-based schedule to facilitate travel experience management and presentation. We show several prototypes in two application scenarios and demonstrate the effectiveness of the proposed system.Chapter 1 Introduction and Related Work 1 1.1 Motivation 1 1.2 Contribution 1 1.3 Related Works 2 1.3.1 Image Retrieval 2 1.3.2 Image Browsing 3 1.4 Thesis Organization 3 Chapter 2 System Framework 5 2.1 The Processing of The User’s Photos 6 2.2 The Reference Images and The Traveling Schedule 7 2.2.1 The Traveling Schedule 7 2.2.2 The Reference Images 8 2.3 The Similarity Between Reference Images and Photo Clusters 8 2.4 The Presentation 9 Chapter 3 The Algorithm of The Processing on User’s Photos 10 3.1 Time Clustering 10 3.2 Day Determination 11 Chapter 4 Similarity Between Reference Images and Photo Clusters 12 4.1 Scale Invariant Feature Transform 12 4.2 The Proposed Method 13 4.3 The Computation Problem and The Solution 14 Chapter 5 Publishing 17 5.1 The Data of Presentation 17 5.1 Webpage 18 5.2 Video 20 Chapter 6 The Extended Work 21 6.1 Extended System Framework 22 6.2 Relation Table 23 6.3 Spot-Photo Matching 25 6.4 Rebuild The Path 25 6.5 Publishing 26 Chapter 7 Experimental Results 28 7.1 Results of Cluster Matching 28 7.2 Relationship between Reference Images and User’s Photos 30 Chapter 8 Conclusion and Future Work 32 8.1 Conclusion 32 8.2 Future Work 32 Reference 332585704 bytesapplication/pdfen-US基於內容的圖像檢索圖像瀏覽尺度不變特徵變換旅遊管理經驗旅行計劃導覽系統Content-based image retrieval (CBIR)Image BrowsingScale Invariant Feature Transform (SIFT)Travel Experience ManagementTravel ScheduleGuide Systemthesishttp://ntur.lib.ntu.edu.tw/bitstream/246246/58414/1/ntu-95-R94944004-1.pdf