Share Email Print

Proceedings Paper

Semantic image retrieval through human subject segmentation and characterization
Author(s): Yanbing Li; Bo Tao; Shun Kei; Wayne H. Wolf
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Video databases can be searched for visual content by searching over automatically extracted key frames rather than the complete video sequence. Many video materials used in the humanities and social sciences contain a preponderance of shots of people. In this paper, we describe our work in semantic image retrieval of person-rich scenes (key frames) for video databases and libraries. We use an approach called retrieval through segmentation. A key-frame image is first segmented into human subjects and background. We developed a specialized segmentation technique that utilizes both human flesh-tone detection and contour analysis. Experimental results show that this technique can effectively segment images in a low time complexity. Once the image has been segmented, we can then extract features or pose queries about both the people and the background. We propose a retrieval framework that is based on the segmentation results and the extracted features of people and background.

Paper Details

Date Published: 15 January 1997
PDF: 12 pages
Proc. SPIE 3022, Storage and Retrieval for Image and Video Databases V, (15 January 1997); doi: 10.1117/12.263422
Show Author Affiliations
Yanbing Li, Princeton Univ. (United States)
Bo Tao, Princeton Univ. (United States)
Shun Kei, Princeton Univ. (United States)
Wayne H. Wolf, Princeton Univ. (United States)

Published in SPIE Proceedings Vol. 3022:
Storage and Retrieval for Image and Video Databases V
Ishwar K. Sethi; Ramesh C. Jain, Editor(s)

© SPIE. Terms of Use
Back to Top