Biometrics is the study of methods for uniquely recognizing humans based on one or more intrinsic physical or behavioral traits. After decades of research activities, biometrics, as a recognized scientific discipline, has advanced considerably both in practical technology and theoretical discovery .They  provide both a concise and accessible introduction to the field as well as a detailed coverage on the unique research problems with their solutions in a wide spectrum of biometrics research ranging from voice, face, fingerprint, iris, handwriting, human behavior to multi-modal biometrics. The contributions also present the pioneering efforts and state-of-the-art results, with special focus on practical issues concerning development through Gait recognition and representation.

How is human identification done by Gait?

There is considerable support for the notion that each person’s gait is unique. It has been observed in literature that people can be recognized by the way they walk. The same notion has been observed in medicine and bio mechanics though not in the context of biometrics but more as an assertion of individuality. Perhaps driven by these notions, though without reference to them, there has been work in psychology on the human ability to recognise each other by using gait. People have also studied walking from medical and bio mechanics perspectives, and this gives insight into how its properties can change which is of general interest in any biometrics.

The coordinated , cyclic combination of movements that result in human locomotion is called Gait.

People often feel that they can identity a familiar person from simply by recognizing the way the person walks.

As a biometric, gait has several attractive properties.

A unique advantage of a gait as a biometric night not be perceivable.

What is gait recognition?

Recognition by gait can be based on the (static) human shape as well as on movement, suggesting a richer recognition cue. It is actually one of the newest biometrics since it’s development is contemporaneous with new approaches in computer vision.

Perhaps driven by these notions, though without reference to them, there has been work in psychology on the human ability to recognise each other by using gait. People have also studied walking from medical and bio mechanics perspective, and this gives insight into how its properties can change which is of general interest in any biometrics.

There are also several confounding properties of gait as a biometric. Unlike fingerprints, we do not know the extent to which an individual’s gait is unique.

What is Score level function?

Since individual features perform different, it is not trivial to combine them. Often this problem is bypassed by concatenating all feature vectors and learning a distance metric for the combined feature vector.

However, to perform well, metric learning approaches need many training samples which are not available in most real-world applications. In contrast, in our approach we perform score-level fusion to combine the matching scores of different features.

To evaluate which score-level fusion techniques perform best for appearance-based person re-identification, we examine several score normalization and feature weighting approaches employing the the widely used and very challenging .

Experiments show that in fusing a large ensemble of features, the proposed score-level fusion approach outperforms linear metric learning approaches which fuse at feature-level.

Furthermore, a combination of linear metric learning and score-level fusion even outperforms the currently best non-linear kernel-based metric learning approaches, regarding both accuracy and computation time.

What is Feature-level fusion?

In feature-level fusion, the feature sets originating from multiple biometric sources are consolidated into a single feature set by the application of appropriate feature normalization, transformation, and reduction schemes.

The primary benefit of feature-level fusion is the detection of correlated feature values generated by different biometric algorithms thereby identifying a compact set of salient features that can improve recognition accuracy.

Eliciting this feature set typically requires the use of  dimensional reduction methods and, therefore, feature-level fusion assumes the availability of a large number of training data. Feature-level fusion algorithms can also be used for template update or template improvement.

What is Support Vector Machine?

The Support Vector Machine (SVM) classifier to recognise defective body gestures.

SVM is an optimal discriminant method based on the Bayesian learning theory. For the cases where it is difficult to estimate the density model in high-dimensional space, the discriminant approach is preferable to the generative approach.

SVM performs an implicitly mapping of data into a higher dimensional feature space, and then finds a linear separating hyper plane with the maximal margin to separate data in this higher dimensional space.

Gait is a biometric, which aims to recognise people from their manner of walking. Unlike other biometrics, gait measurement is unobtrusive and can be captured at a distance. Moreover, it can be detected and measured at low resolution.

In contrast, most other biometrics such as fingerprint , face, iris ,signature and voice are restricted to controlled environments.

They can be captured only by physical contact or at a close distance from the probe. Even face and iris requires a high-resolution probe.

Gait can thus be alternatively used in situations where other biometrics might not be applicable.

Therefore, there has been an increase in research related to gait recognition over recent years.

These new approaches require good computer memory and processing speed to processes sequences of image data with reasonable performance.

There are also several confounding properties of gait as a biometric. Unlike fingerprints, we do not know the extent to which an individual’s gait is unique.

What is Gait representation?

Gait representation consists of a Motion Intensity Image , which measures the intensity of relative motion at each pixel location, and four Motion Direction Images , each of which represents the likelihood of the direction of motion being along one specific motion direction during a complete gait.

 How can  identification be done with template based on the width of a silhouette image?

A simple baseline method for human identification based on body shape and gait. This baseline recognition method provides a lower bound against which to evaluate more complicated procedures.

They  present a viewpoint dependent technique based on template matching of body silhouettes. Cyclic gait analysis is performed to extract key frames from a test sequence.

These frames are compared to training frames using normalized correlation, and subject classification is performed by nearest neighbor matching among correlation scores.

The approach implicitly captures biometric shape cues such as body height, width, and body-part proportions, as well as gait cues such as stride length and amount of arm swing. They  evaluate the method on four databases with varying viewing angles, background conditions (indoors and outdoors), walk styles and pixels on target.

How can features be  identified with template based on projection of a silhouette image?

They present a novel, fast, resolution-independent silhouette area-based matching approach.

We approximate the silhouette area by a small set of axis-aligned rectangles.

This yields a very memory efficient representation of templates. In addition, utilizing the integral image, we can thus compare a silhouette with an input image at an arbitrary position in constant time.

Furthermore, we present a new method to build a template hierarchy optimized for our rectangular representation of template silhouette.

Gait is a biometric, which aims to recognise people from their manner of walking. Unlike other biometrics, gait measurement is unobtrusive and can be captured at a distance. Moreover, it can be detected and measured at low resolution.

In contrast, most other biometrics such as fingerprint , face, iris ,signature and voice are restricted to controlled environments.

They can be captured only by physical contact or at a close distance from the probe. Even face and iris requires a high-resolution probe.

Gait can thus be alternatively used in situations where other biometrics might not be applicable.

Therefore, there has been an increase in research related to gait recognition over recent years.