Multimedia Indexing and Retrieval Research at the Center for Intelligent Information Retrieval

摘要

The digital libraries of the future will include not only (ASCII) text information but scanned paper documents as well as still photograph and videos. There is, therefore, a need to index and retrieve information from such multi-media collections. The Center for Intelligent Information Retrieval (CIIR) has a number of projects to index and retrieve multi-media information. These include: 1. The extraction of text from images which may be used both for finding text zones against general backgrounds as well as for indexing and retrieving image information. 2. Indexing hand-written and poorly printed documents using image matching techniques (word spotting). 3. Indexing images using their content.