Content-based image retrieval (CBIR), also known as image content query (QBIC) and content-based visual information retrieval (CBVIR), is the application of computer vision to the problem of image retrieval, ie , the problem of looking for images in large databases.
"Content-based" means that the search will analyze the actual content of the image. The term 'content' in this context may refer to colors, shapes, textures or any other information that may be derived from the image itself. Without the ability to examine the content of the image, searches should be based on metadata, such as legends or keywords. Such metadata must be generated by a human and stored next to each image in the database.
Problems with traditional image indexing methods have sparked interest in techniques for retrieving images based on automatically derived features, such as color, texture and shape, a technology now known as Content Based Image Recovery ( CBIR). However, the technology still lacks maturity and is not yet being used on a significant scale. In the absence of strong evidence on the effectiveness of CBIR techniques in practice, opinion is still very divided about its usefulness in handling real-life consultations in large and diverse image collections. The concepts that are currently used for the CBIR system are all under investigation.