臺灣博碩士論文加值系統

隨著網際網路的快速發展，在WWW上已經擁有非常巨量的網頁和圖片，從另一個角度來看，WWW就像是龐大的圖片資料庫，所以，圖片搜尋引擎最主要的目的就是讓使用者可以方便又快速地找到想要的圖片。
在本篇論文中，將會著重在以關鍵字為主的搜尋方法，經由網頁的分析，找出與圖片相關的文字，進而實作出一套完整的系統，讓使用者可以透過關鍵字來查詢圖片，另外，在輸出查詢結果時，我們提供了一些技巧，可以用來改善查詢結果的正確性。

There are large number of web pages and images in the WWW because of the rapid growth of Internet. In some sense, the WWW is like a database which contains a huge number of images. Therefore, the main purpose of the image search engine is to help users quickly find the images which they want with convenience.
In the thesis, we will focus on keyword-based image search methods, find the words related to images according to the analysis of web pages, and develop a search engine that let users search the images by query words. In addition, before output the results, we propose some technique which can improve the accuracy of query results.

1.簡介
2.系統架構
3.網頁分析
4.圖片的處理
5.分數的計算
6.實驗
7.結論與未來展望
8.參考資料

G. Qiu and R. Palmer, “WISE: A Content-based Web Image Search Engine”, Multimedia Computing and Networking 2001, January 21-26, 2001, San Jose, CA, USA
Neil C. Rowe, “Marie-4: A High-Recall, Self-Improving Web Crawler That Finds Images Using Captions”, IEEE Intelligent Systems, Vol. 17, No. 4, July/August 2002
C. Framkel, M.J. Swain, and V. Athitsos, “Webseer: An image search engine for the world wide web”, Tech. Rep. Tr-96-14, University of Chicago, 1996