Precise and Efficient Retrieval of Captioned Images: The MARIE Project
Loading...
Authors
Rowe, Neil C.
Subjects
Advisors
Date of Issue
1999
Date
Fall 1999
Publisher
Monterey, CA; Naval Postgraduate School
Language
Abstract
The 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 domain-independent 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.
Type
Article
Description
This paper appeared in Library Trends, Fall 1999.
Series/Report No
Department
Computer Science (CS)
Organization
Identifiers
NPS Report Number
Sponsors
supported by the U.S. Army Artificial Intelligence Center, and by the U. S. Naval Postgraduate School
Funding
funds provided by the Chief for Naval Operations
Format
Citation
Distribution Statement
Approved for public release; distribution is unlimited.