06-03-2013, 11:06 AM
HUMAN IDENTIFICATION USING TEMPORAL INFORMATION PRESERVING GAIT TEMPLATE
PRESERVING GAIT TEMPLATE.doc (Size: 5.21 MB / Downloads: 89)
Abstract:
Gait Energy Image (GEI) is an efficient template for human identification by gait. However, such a template loses temporal information in a gait sequence, which is critical to the performance of gait recognition. To address this issue, we develop a novel temporal template, named Chrono-Gait Image (CGI), in this paper. The proposed CGI template first extracts the contour in each gait frame, followed by encoding each of the gait contour images in the same gait sequence with a multichannel mapping function and compositing them to a single CGI. To make the templates robust to a complex surrounding environment, we also propose CGI-based real and synthetic temporal information preserving templates by using different gait periods and contour distortion techniques. Extensive experiments on three benchmark gait databases indicate that, compared with the recently published gait recognition approaches, our CGI-based temporal information preserving approach achieves competitive performance in gait recognition with robustness and efficiency.
INTRODUCTION
BIOMETRIC authentication has broad applications in social security, individual identification in law enforcement, and access control in surveillance. Unlike other biometric features such as iris, faces, palm, and fingerprint, the advantages of gait include: 1) Gait can be collected in a noncontactable, noninvasive, and hidden manner; 2) gait is the only perceptible biometric at a distance. However, the performance of gait recognition suffers from some exterior factors such as clothing, shoes, briefcases, and environmental context. Furthermore, whether or not the spatiotemporal relationship between gait frames in a gait sequence is effectively represented also influences the performance of gait recognition systems. Although it is a challenging task, the nature of gait indicates that it is an irreplaceable biometric and can benefit the remote biometric authentication. To build a successful gait recognition system, feature extraction plays a crucial role. Currently, gait feature extraction methods can be roughly divided into two major categories: model-based and model-free approaches. Model based approaches assume that the gait can be modeled with a structure/motion model. However, it is not easy to extract the underlying model from gait sequences. Model free approaches either keep temporal information in the recognition (and training) stage or convert a sequence of images into a single template. Although some model-free approaches such as Gait Energy Image (GEI) have attractively low computational cost, such a conversion may lose the temporal information of gait sequences.
Existing System:
Unlike other biometric features such as iris, faces, palm, and fingerprint, the advantages recognition suffers from some exterior factors such as clothing, shoes, briefcases, and environmental context. Furthermore, whether or not the spatiotemporal relationship between gait frames in a gait sequence is effectively represented also influences the performance of gait recognition systems. Although it is a challenging task, the nature of gait indicates that it is an irreplaceable biometric and can benefit the remote biometric authentication of gait include:
1) Gait can be collected in a non-contactable, noninvasive, and hidden manner;
2) Gait is the only perceptible biometric at a distance. However, the performance of gait.
Proposed System:
To build a successful gait recognition system, feature extraction plays a crucial role. Currently, gait feature extraction methods can be roughly divided into two major categories: model-based and model-free approaches. Model based approaches assume that the gait can be modeled with a structure/motion model. However, it is not easy to extract the underlying model from gait sequences. Model free approaches either keep temporal information in the recognition (and training) stage, or convert a sequence of images into a single template. Although some model-free approaches such as Gait Energy Image (GEI) have attractively low computational cost, such a conversion may lose the temporal information of gait sequences.
The Java Platform:
A platform is the hardware or software environment in which a program runs. We’ve already mentioned some of the most popular platforms like Windows 2000, Linux, Solaris, and MacOS. Most platforms can be described as a combination of the operating system and hardware. The Java platform differs from most other platforms in that it’s a software-only platform that runs on top of other hardware-based platforms.
Working Of Java:
For those who are new to object-oriented programming, the concept of a class will be new to you. Simplistically, a class is the definition for a segment of code that can contain both data and functions.When the interpreter executes a class, it looks for a particular method by the name of main, which will sound familiar to C programmers. The main method is passed as a parameter an array of strings (similar to the argv[] of C), and is declared as a static method.
To output text from the program, iexecute the println method of System. out, which is java’s output stream. UNIX users will appreciate the theory behind such a stream, as it is actually standard output. For those who are instead used to the Wintel platform, it will write the string passed to it to the user’s program.
CONCLUSIONS AND FUTIRE WORK
In this paper, we have proposed a simple but effective temporal information preserving template CGI for gait recognition. We extract a set of contour images from the corresponding silhouette I ages using the local entropy rinciple, and encode the temporal information of gait sequence into the CGI using the multichannel technique. We also generate CGI-based real and synthetic temporal templates and exploit the fusion strategy to obtain better performance. Experiments on three benchmark databases have demonstrated that compared with state-of-the-art algorithms, ourCGItemplate can attain higher or comparable recognition accuracy with good robustness .