Precise and Efficient Retrieval of Captioned Images: The MARIE Project
Rowe, Neil C.
MetadataShow full item record
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 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.
This paper appeared in Library Trends, Fall 1999.
Showing items related by title, author, creator and subject.
Janecek, James Frank. (1985);Segmentation is an important step in the computer based analysis of images. This thesis addresses the segmentation of images of multiple channels of data. Such images are referred to as multichannel images. Examples of ...
Corley, M.S.; Santiago, F.; T. Martinez; Agrawal, B.N. (2011);The Navy is interested in horizontal laser propagation studies in a maritime environment, near the ocean surface, for applications including imaging and high-energy laser propagation. The Naval Postgraduate School (NPS) ...
Karavas, Panagiotis (Monterey, California ; Naval Postgraduate School, 1999);Until recently no standard atmospheric propagation codes included the effects of polarization. Recently a research grade upgrade to MODTRAN (Zeisse, Nrad) has allowed the polarized case. This upgrade, called SEARAD, ...