Content-Based Image Retrieval

摘要: With today’s large increase in digital images and automatically generated imagery, such as videos stills from surveillance equipment, the need for efficient image retrieval indexing has become fundamental. Since text-based information been shown to perform very poorly when searching through images, research active field of content-based (CBIR). CBIR systems make use properties order compare them extract content by matching query image. Comparing features – color, texture, shape allows better accuracy; however, algorithms used are still limited. This paper will provide a survey explain fundamental techniques these systems. First, history be discussed together with some typical After this, touch on why it does not work collections images. The latter portion this document provides an overview system main involved querying system. Finally, schemes described.