Share Email Print
cover

Proceedings Paper

Human posture recognition using curved segments for image retrieval
Author(s): JongSeung Park; HwangSeok Oh; DukHo Chang; EeTack Lee
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

This paper presents a human posture recognition method form a single image. We first segment an image into homogeneous regions and extract curve segments corresponding to human body parts. Each body part is considered as a 2D ribbon. From the smooth curve segments in skin regions, 2D ribbons are extracted and a human body model is constructed. We assign a predefined posture type to the image according to the constructed body model. For the user input query to retrieve images containing human of specific posture, the system convert the query to a body model. The body model is compared to other body models saved in the local storage of target images and images of good matches are retrieved. When a face detection result is available for the given image, it is also used to increase the reliability of body model. For the query human posture, our system retrieves images of the corresponding posture. As another application, the proposed method provides an initial location of a human body to track in a video sequence.

Paper Details

Date Published: 23 December 1999
PDF: 10 pages
Proc. SPIE 3972, Storage and Retrieval for Media Databases 2000, (23 December 1999); doi: 10.1117/12.373539
Show Author Affiliations
JongSeung Park, Electronics and Telecommunications Research Institute (South Korea)
HwangSeok Oh, Electronics and Telecommunications Research Institute (South Korea)
DukHo Chang, Electronics and Telecommunications Research Institute (South Korea)
EeTack Lee, Electronic Telecommunication Research Institute (South Korea)


Published in SPIE Proceedings Vol. 3972:
Storage and Retrieval for Media Databases 2000
Minerva M. Yeung; Boon-Lock Yeo; Charles A. Bouman, Editor(s)

© SPIE. Terms of Use
Back to Top