Human Identification Based Biometric Gait Features using MSRC Human Identification Based Biometric Gait Features using MSRC
Journal Title: International Journal of Advanced Research in Computer Engineering & Technology(IJARCET) - Year 2013, Vol 2, Issue 5
Abstract
Human identification using gait is a new biometric intended to classify individuals by the way they walk have come to play an increasingly important role in visual surveillance applications. In gait biometric research, various gait classification approaches are available. This paper presents human identification system using the view-invariant approach. The framework of proposed system consists of the subject detection, silhouette extraction, feature extraction, and classification. Firstly, moving subjects are detected from the video sequences. And extractions of human silhouette are done by using background subtraction method. In feature extraction step, motion parameters such as joint angles, angular velocity and gait velocity are calculated using speeded up robust features (SURF) descriptors. This descriptor helps to read the essential points used to generate gait signatures and extracts motion parameters for classification. In the final stage, Meta-sample based sparse representation method (MSRC) is used in classification of the extracted motion parameters and features. Experiments are conducted on the own dataset which obtain overall classification rate of 94.6782%.
Authors and Affiliations
Nyo Nyo Htwe , Nu War,
Keywords
Related Articles
- EP ID EP98873
- DOI -
- Views 101
- Downloads 0
A Comparative Study On Some New Steganographic Techniques
In this paper, we present some new methods and develop techniques with algorithms for hiding text behind the gray scale image. Steganographic technique allows the sender to communicate information to the receiver w...
Image segmentation based on kernel fuzzy C means clustering using edge detection method on noisy images
Classical fuzzy C-means (FCM) clustering is performed in the input space, given the desired number of clusters. Although it has proven effective for spherical data, it fails when the data structure of input pattern...
Assessing Quality of Software Service at Selection Time Using Evolutionary Algorithm
The integration of external software in project development can be challenging and risky, because as the execution quality of the external software and the trustworthiness of the software is unknown during integrat...
Analysis of local and global techniques for disparity map generation in stereo vision
The field of computer vision is still open to generate 3D images (depth) using stereo image pairs. Obtaining reliable depth estimation has importance in robotic applications and autonomous systems. Stereo vision is...
A Combined Approach to Part-of-Speech Tagging Using Features Extraction and Hidden Markov Model
Words are characterized by its features. In an inflectional language, category of a word can be express by its tense, aspect and modality (TAM). Extracting features from an inflected word, one can categorised it wi...