28 May 2003 Body shape variability problem in Eigenspace
Author Affiliations +
Abstract
This paper claims that human various body shapes create individual eigenspaces; as a result, the classical appearance-based model cannot be effective for recognizing human postures. We introduce figure effect in the eigenspaces due to different human body shapes in this particular study. The study proposes an organized eigenspace tuning method for overcoming the preceding problem. Since the proposed method tunes the classical eigenspaces for human posture recognition, we define this phenomenon eigenspace tuning. Generation of a tuned eigenspace (TES) is an organized method where some of similar eigenspaces are selected according to MDD (minimum description deviation) method and a mean if them is taken. In fact, the TES is an optimized visual appearance of various human models that minimizes the fluctuation of MDL (mean description length) between training and testing feature spaces. We have tested the proposed approach on a number of human models considering their various body shapes, and significance of the method to the recognition rates has been demonstrated.
© (2003) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
M. Masudur Rahman, M. Masudur Rahman, Seiji Ishikawa, Seiji Ishikawa, } "Body shape variability problem in Eigenspace", Proc. SPIE 5014, Image Processing: Algorithms and Systems II, (28 May 2003); doi: 10.1117/12.479693; https://doi.org/10.1117/12.479693
PROCEEDINGS
8 PAGES


SHARE
RELATED CONTENT

Video inpainting using scene model and object tracking
Proceedings of SPIE (February 18 2013)
COM-based scene segmentation in news video
Proceedings of SPIE (November 03 2005)
WeatherDigest: an experiment in media conversion
Proceedings of SPIE (January 02 1996)
Static hand gesture recognition from a video
Proceedings of SPIE (September 30 2011)

Back to Top