由於電腦與網路科技的發達，多媒體資料：圖片、聲音因此蓬勃發展，多媒體資料量成長速度亦是驚人。人們要如何面對這個“資料爆炸”的時代呢？透過電腦幫我們前置處理，能節省時間與人力。所以針對影像理解這個議題，我們提出利用知識本體論輔助電腦系統理解影像，並進而達成自動影像註解。
在過去的影像檢索系統中，系統利用低階特徵：顏色、紋理、形狀去分析影像，但是這樣做並沒有如人們以影像的內容語意及實體物件為單位作考量，導致電腦沒有真正理解影像，拿這樣的結果運用到影像檢索、影像辨識、影像自動註解，常常會產生錯誤，效果不彰。故我們提出以低階特徵為基礎，利用本體論建構的知識幫助電腦分析影像中的實體物件，讓電腦更精準了解影像中所包含物件及其深層的語意，也能了解物件與物件間在真實世界中合理的相關性。並進而對影像註解不僅用關鍵字也包含一些描述性、位置關係表示的語意註解。這樣未來可被應用在使用者運用自然語言表達來搜尋自己所要的影像。
我們最後實驗以低階特徵辨識註解影像與加入本體論輔助註解影像的結果作比較，的確，本體論有助於電腦對影像的理解，影像物件的辨識準確度均有提升。最後我們展示系統能作圖像關鍵字註解，區塊命名與描述性註解。

Due to the advance in computer and network technology, the amount of multimedia data, such as images and sounds, makes organizing them an arduous task. How do we deal with this enormous amount of data? We preprocess the data with computer to increase time efficiency and save manpower. We analyze images and make automated annotations via previously built ontology.
The past image retrieval systems utilize low-level features such as color, texture and shape, to analyze images, but this does not take semantics of content and physical objects into account which usually leads to misunderstanding of images and false indexing, recognition, and annotation. We propose a method that applies semantics of content on analysis of physical objects in images, so computers can accurately detect objects, deduce the relations between objects and extract the underlying semantics. With sufficient annotations, users can query desired images with natural language in the future.
Comparing between conventional low-level annotations and our newly proposed ontology-based annotations, ontology enhances the comprehension of images by computers, and the accuracy of object recognition is also increased. We will demonstrate the ability of keywords annotation, region naming, and descriptively commenting in our system.

[01] 林忠誠，基於本體論與標準物件以遞增式學習來理解影像，國立清華大學碩士論文，2004年。
[02] 謝秉諺，利用隱馬可夫模型進行風景影像之語意分析，國立中正大學碩士論文，2002年。
[03] Lindsay I Smith, A Tutorial on Principal Components Analysis, February 2002.
[04] James Z. Wang, Jia Li, Gio Wiederhold, SIMPLIcity: Semantics-Sensitive Integrated Matching for Picture Libraries, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 23, NO. 9, September 2001.
[05] D. Comaniciu, P. Meer, Mean shift, A robust approach toward feature space analysis, IEEE Transactions on Pattern Analysis and Machine Intelligence, 24, 603-619, 2002.
[06] T. Kohonen, The self-organization map, Proceedings of the IEEE, vol. 78, No. 9, September 1990.
[07] Pinar Duygulu, Translating Images to Words: A Novel Approach for Object Recognition, February 2003.
[08] Von-Wun Soo, Karen Huang, On Evidential Relaxation Labeling –A Scheme Toward Knowledge-Based Vision, Journal of Information Science and Engineering, vol.9 No.2, pp.153-175, June 1993.
[09] Jean-Pierre Schober, Thorsten Hermes, Otthein Herzog, Content-based Image Retrieval by Ontology-based Object Recognition, Proceedings of the KI-2004 Workshop on Applications of Description Logics, September 2004.
[10] Alicia Abella, John R. Kender, From Images to Sentences via Spatial Relations, Proceedings of the Integration of Speech and Image Understanding, pp. 117-146,1999.
[11] Alicia Abella, John R. Kender, Qualitatively Describing Objects Using Spatial Prepositions, IEEE Workshop on Qualitiative Vision, 1993.
[12] Laura Hollink, Giang Nguyen, Guus Schreiber, Jan Wielemaker, Bob Wielinga, Marcel, Adding Spatial Semantics to Image Annotations, 4th International Workshop on Knowledge Markup and Semantic Annotation at ISWC, 2004.
[13] WEKA, http://www.cs.waikato.ac.nz/~ml/weka/index.html
[14] Chen-Yu Lee, Von-Wun Soo, and Yi-Ting Fu, How to annotate an image? The Need of an Image Annotation Guide Agent, ACM/IEEE International Joint Conference of Digital Library 2004.
[15] Von-Wun Soo, Chen-Yu Lee, Chao-Chun Yeh and Ching-chih Chen, Using Sharable Ontology to Retrieve Historical Images, ACM/IEEE International Joint Conference of Digital Library 2002.
[16] W3C, http://www.w3c.org
[17] Lei Zhu, Geoblock: A LVQ-based Framework for Geographic Image Retrieval, ITCC, vol. 02, no. 2, p. 8, 2004.
[18] Kobus Barnard and David Forsyth, Learning the Semantics of Words and Pictures, International Conference on Computer Vision, vol 2, pp. 408-415, 2001.
[19] Darrin Cardani, Adventures in HSV Space, July, 2001.
[20] Arfken, G, Discrete Orthogonality--Discrete Fourier Transform , Mathematical Methods for Physicists, 3rd ed. Orlando, FL: Academic Press, pp. 787-792, 1985.