應用於拍賣網頁分類目錄下的影像搜尋系統

近年來，隨著多媒體資訊的普及，數位相機、具有照像功能的手機等相關科技產品的普及化，許多研究學者開始採用影像的內容來做為圖片搜尋的依據。本篇論文主要是將此方法應用在Yahoo拍賣網頁上，並且在特定的分類目錄底下，實做一個影像搜尋系統。本搜尋系統，提供使用者上傳或點選資料庫中影像做搜尋；根據輸入的影像，首先利用了最基本的Whole Image來做特徵擷取，最後回傳拍賣網頁中最相似的圖片及拍賣網頁的網址以供使用者瀏覽。為了增進基本影像搜尋的準確率，本論文中我們提出了" Edge + PCA "的方法來取出影像中具有意義、有代表性的區域，並擷取此區域的特徵進行搜尋，回傳結果供使用者瀏覽。除此之外，我們還結合影像內容和文字來做搜尋，提供給使用者更有效率且準確的影像搜尋結果。最後，我們根據Yahoo拍賣網頁抓取的資料來做系統的評估。

關鍵字

搜尋系統；線上圖片搜尋系統；色彩直方圖；區域檢索

並列摘要

Because of the advancement of multimedia technology and the popularity of digital cameras, camera-enabled mobile phone, and Internet, many researchers have recently studied to use the content of images for image retrieval. The purpose of this paper is to apply content-based image retrieval to online auction system with build-in directories. The development of an intelligent category- and content-based search engine is presented, in which it allows a user to upload an image file or choose one image from database to search. In the baseline system, we extract features from the whole image and the system returns images with similar features and also their hyperlinks to the source auction webpages for browsing. To improve the precision of image search, we propose a novel approach to extract features from the most likely object region in an image, called "Edge + PCA". The approach assumes that there is rich edge information around the object in an image. A representative region is calculated from the edge map of an image using PCA. In addition, we combine image search with text search to provide users more flexibility and examine its performance against image-only and text-only search. In the experiments, we downloaded images and related webpages from Yahoo online auction and evaluated the performance of the proposed systems.

並列關鍵字

Edge；PCA；CBIR；Color Histogram；Content-Based Image Retrieval

參考文獻

[1] M. Flickner, H. Sawhney, W. Niblack, J. Ashley, Q. Huang, B. Dom, M. Gorkani, J. Hafner, D. Lee, D. Petkovic, D. Steele, and P. Yanker, "Query by image and video content: The QBIC system." IEEE Computer, vol. 28, pp. 23-32, Sept, 1995.

Google Scholar

[2] W. Niblack, R. Barber, W. Equitz, M. Flickner, E. Glasman, D. Petkovic, P. Yanker, C. Faloutsos and G. Taubin, "The QBIC project: Querying images by content using colour, texture and shape, " in Proceedings of the SPIE on Storage and Retrieval for Image and Video Databases, vol. 1908, pp. 173-187, 1993.