Translator Disclaimer
23 December 1999 Human posture recognition using curved segments for image retrieval
Author Affiliations +
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.
© (1999) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
JongSeung Park, HwangSeok Oh, DukHo Chang, and EeTack Lee "Human posture recognition using curved segments for image retrieval", Proc. SPIE 3972, Storage and Retrieval for Media Databases 2000, (23 December 1999);


Foreground detection for content-based image retrieval
Proceedings of SPIE (March 12 2013)
Adaptive skin detection based on online training
Proceedings of SPIE (November 14 2007)
Multi-skin color clustering models for face detection
Proceedings of SPIE (February 26 2010)
Real-time face tracking
Proceedings of SPIE (October 05 1998)

Back to Top