| Content-based visual information retrieval (CBVIR) is one of the most interesting research topics in the last years for the image and video community. With the progress of electronic equipment and computer techniques for visual information capturing and processing, a huge number of image and video records have been collected. Visual information becomes a well-known information format and a popular element in all aspects of our society. The large visual data make the dynamic research focused on the problem of how efficiently to capture, store, access, process, represent, describe, query, search, and retrieve their contents. In the last years, this field has experienced significant growth and progress, resulting in a virtual explosion of published information.
The research on CBVIR has already a history of more than a dozen years. It was started by using low-level features, such as color, texture, shape, structure, and space relationship, as well as (global and local) motion to represent the information content. Research on feature-based visual information retrieval has made quite a bit, but limited, success. Due to the considerable difference between the users’ concerns on the semantic meaning and the appearances described by the aforementioned low-level features, the problem of semantic gap arises. One has to shift the research toward some high levels, and especially the semantic level. So, semantic-based visual information retrieval (SBVIR) began a few years ago and soon became a notable theme of CBVIR.
Research on SBVIR is conducted around various topics, such as (in an alpha-beta list) distributed indexing and retrieval, higher-level interpretation, human-computer interaction, human knowledge and behavior, indexing and retrieval for huge databases, information mining for indexing, machine-learning approaches, news and sport video summarization, object classification and annotation, object recognition and scene understanding, photo album and storybook generation, relevance feedback and association feedback, semantic modeling for retrieval, semantic representation and description, semiotics and symbolic operation, video abstraction and structure analysis, and so forth. |
