Automated body feature extraction from 2D images

► Body feature points can be extracted from front and side images. ► A shape coding algorithm detects the variation of the human body silhouette. ► The extracted feature points can be processed to collect anthropometric data. Extracting human body features automatically from 2D images provides a fas...

Full description

Saved in:
Bibliographic Details
Published in:Expert systems with applications Vol. 38; no. 3; pp. 2585 - 2591
Main Authors: Lin, Yueh-Ling, Wang, Mao-Jiun J.
Format: Journal Article
Language:English
Published: Elsevier Ltd 01.03.2011
Subjects:
Body feature points
Contour representation
Human feature extraction
Shape description
Shape description
Contour representation
Body feature points
Human feature extraction
ISSN:0957-4174, 1873-6793
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:► Body feature points can be extracted from front and side images. ► A shape coding algorithm detects the variation of the human body silhouette. ► The extracted feature points can be processed to collect anthropometric data. Extracting human body features automatically from 2D images provides a fast and easy approach to collect anthropometric data. This paper presents a systematic method to detect feature points on the silhouette of human body from the front and side images. With an efficient shape coding algorithm, the human body contour of the binary images can be represented. By evaluating the difference between the coding sequence, feature points can be identified. Hence, a total of 60 feature points can be extracted automatically. The method has been tested on 30 human subjects and all the feature points can be correctly extracted. In order to evaluate the performance of the automatic body feature extraction system, the feature points obtained from the proposed method were validated by analyzing the location variation of the silhouette curve. The experimental results indicate that the system is very effective and robust. Moreover, the extracted feature points can be subsequently processed for body dimension measurements. Thus, the newly developed system can achieve an automated extraction of body features and to obtain anthropometric data for many applications.
ISSN:0957-4174
1873-6793
DOI:10.1016/j.eswa.2010.08.048