Research Article | OPEN ACCESS
Elliptical Model for Normal and Abnormal Gait Classification
1S.M.H. Sithi Shameem Fathima and 2R.S.D. Wahida Banu
1Syed Ammal Engineering College, Ramanathapuram, India
2Government College of engineering, Salem, India
Research Journal of Applied Sciences, Engineering and Technology 2015 11:1238-1244
Received: July ‎24, ‎2015 | Accepted: September ‎14, ‎2015 | Published: December 15, 2015
Abstract
The proliferation of innovative recognition and surveillance systems encompasses several algorithms and techniques. Human gait based recognition system, a subset of behaviour-based biometrics such as style, skills, language designs, support recognition and surveillance. In this manuscript, we propose to classify human gait as normal gait or abnormal gait through silhouette reconstruction and ellipse-fitting model. In ellipse-fitting, this article proposes a novel method of expanding the bounding box by covering human gait from head to toe for providing robust information about an individual as compared to the contemporary methodologies that acquire gait features from head to ankle. The other objective of this study is emphasizing the requirement of storing abnormal human gaits in databases for efficient recognition and surveillance, thereby improving the processing time coupled with the recognition rate. The Sparse Representation classifier (SRC) automatically classifies the normal and abnormal gait based on the characteristic vectors. The solicitation of 105 subjects facilitated the definition of the test sample. A camera with lower resolution recorded each subjects’ images of normal and abnormal walking pattern. An extensive iterative process determined that the proposed method achieved 99.52 % classification accuracy, using SRC in contrast to the state of the art methodologies and basic classifiers.
Keywords:
Ellipse-fitting, elliptical feature extraction, features vectors, gait classification, silhouette reconstruction, sparse representation classifier,
Competing interests
The authors have no competing interests.
Open Access Policy
This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.
Copyright
The authors have no competing interests.
|
|
![](http://www.maxwellsci.com/images/RJASET-maxw.jpg) |
ISSN (Online): 2040-7467
ISSN (Print): 2040-7459 |
![Submit Manuscript](../images/sub.jpg) |
Information |
|
|
|
Sales & Services |
|
|
|