An Intelligent Content-based Image Retrieval System Based on Color, Shape and Spatial Relations

• Main Authors: Ching-Sheng Wang, 王慶生
• Other Authors: Prof. Timothy, K. Shih
• Format: Others
• Language: en_US
• Published: 2001
• Online Access: http://ndltd.ncl.edu.tw/handle/06639395180098015639

博士 === 淡江大學 === 資訊工程學系 === 89 === Content-based image retrieval has become more desirable for developing large image database. This thesis presents an intelligent method of retrieving images from an image database. This system combines color, shape and spatial features to index and measure similarity of images. Several color spaces that widely used in computer graphic were discussed and compared for color clustering. In addition, this dissertation propose a new automatic indexing scheme of image database according to our clustering method and color sensation, which could be used to retrieve image efficiently. As a technical contribution, a Seed-Filling like algorithm that could extract the shape and spatial relationship feature of image is proposed. Due to the difficulty of determining how far objects are separated, this system uses qualitative spatial relations to analyze object similarity. Also, the system is incorporated with a visual interface and a set of tools, which allows the users to express the query by specify or sketch the images conveniently. Besides, the feedback learning mechanism enhances the precision of retrieval. The experience shows that the system is able to retrieve image information efficiently by the proposed approaches.