Show simple item record

dc.contributor.authorRowe, Neil C.
dc.dateFall 1999
dc.date.accessioned2013-09-20T16:58:42Z
dc.date.available2013-09-20T16:58:42Z
dc.date.issued1999
dc.identifier.urihttp://hdl.handle.net/10945/36580
dc.descriptionThis paper appeared in Library Trends, Fall 1999.en_US
dc.description.abstractThe MARIE project has explored knowledge-based information retrieval of captioned images of the kind found in picture libraries and on the Internet. It exploits the idea that images are easier to understand with context, especially descriptive text near them, but it also does image analysis. The MARIE approach has five parts: (1) Find the images and captions; (2) Parse and interpret the captions; (3) Segment the images into regions of homogeneous characteristics and classify them; (4) Correlate caption interpretation with image interpretation, using the idea of focus; (5) Optimize query execution at runtime. MARIE emphasizes domainindependent methods for portability at the expense of some performance, although some domain specification is still required. Experiments show MARIE prototypes are more accurate than simpler methods, although the task is very challenging and more work is needed. Its processing is illustrated in detail on part of a Internet World Wide Web page.en_US
dc.description.sponsorshipsupported by the U.S. Army Artificial Intelligence Center, and by the U. S. Naval Postgraduate Schoolen_US
dc.publisherMonterey, California. Naval Postgraduate Schoolen_US
dc.rightsApproved for public release, distribution unlimiteden_US
dc.titlePrecise and Efficient Retrieval of Captioned Images: The MARIE Projecten_US
dc.contributor.departmentComputer Science
dc.description.funderfunds provided by the Chief for Naval Operationsen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record