Summary: | 碩士 === 國立暨南國際大學 === 資訊工程學系 === 96 === 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.
|