John N. Carter

Automatic extraction and description of human gait models for recognition purposes

Using gait as a biometric is of emerging interest. We describe a new model-based moving feature extraction analysis is presented that automatically extracts and describes human gait for recognition. The gait signature is extracted directly from the evidence gathering process. This is possible by using a Fourier series to describe the motion of the upper leg and apply temporal evidence gathering techniques to extract the moving model from a sequence of images. Simulation results highlight potential performance benefits in the presence of noise. Classification uses the k-nearest neighbour rule applied to the Fourier components of the motion of the upper leg. Experimental analysis demonstrates that an improved classification rate is given by the phase-weighted Fourier magnitude information over the use of the magnitude information alone. The improved classification capability of the phase-weighted magnitude information is verified using statistical analysis of the separation of clusters in the feature space. Furthermore, the technique is shown to be able to handle high levels of occlusion, which is of especial importance in gait as the human body is self-occluding. As such, a new technique has been developed to automatically extract and describe a moving articulated shape, the human leg, and shown its potential in gait as a biometric.

Automated person recognition by walking and running via model-based approaches

Gait enjoys advantages over other biometrics in that it can be perceived from a distance and is di cult to disguise.Current approaches are mostly statistical and concentrate on walking only.By analysing leg motion we show how we can recognise people not only by the walking gait,but also by the running gait.This is achieved by either of two new modelling approaches which employ coupled oscillators and the biomechanics of human locomotion as the underlying concepts.These models give a plausible method for data reduction by providing estimates of the inclination of the thigh and of the leg,from the image data. Both approaches derive a phase-weighted Fourier description gait signature by automated non-invasive means.One approach is completely automated whereas the other requires speci cation of a single parameter to distinguish between walking and running.Results show that both gaits are potential biometrics,with running being more potent.By its basis in evidence gathering,this new technique can tolerate noise and low resolution.

Force field feature extraction for ear biometrics

The overall objective in defining feature space is to reduce the dimensionality of the original pattern space, whilst maintaining discriminatory power for classification. To meet this objective in the context of ear biometrics a new force field transformation treats the image as an array of mutually attracting particles that act as the source of a Gaussian force field. Underlying the force field there is a scalar potential energy field, which in the case of an ear takes the form of a smooth surface that resembles a small mountain with a number of peaks joined by ridges. The peaks correspond to potential energy wells and to extend the analogy the ridges correspond to potential energy channels. Since the transform also turns out to be invertible, and since the surface is otherwise smooth, information theory suggests that much of the information is transferred to these features, thus confirming their efficacy. We previously described how field line feature extraction, using an algorithm similar to gradient descent, exploits the directional properties of the force field to automatically locate these channels and wells, which then form the basis of characteristic ear features. We now show how an analysis of the mechanism of this algorithmic approach leads to a closed analytical description based on the divergence of force direction, which reveals that channels and wells are really manifestations of the same phenomenon. We further show that this new operator, with its own distinct advantages, has a striking similarity to the Marr-Hildreth operator, but with the important difference that it is non-linear. As well as addressing faster implementation, invertibility, and brightness sensitivity, the technique is also validated by performing recognition on a database of ears selected from the XM2VTS face database, and by comparing the results with the more established technique of Principal Components Analysis. This confirms not only that ears do indeed appear to have potential as a biometric, but also that the new approach is well suited to their description, being robust especially in the presence of noise, and having the advantages that the ear does not need to be explicitly extracted from the background.

On a Large Sequence-Based Human Gait Database

Biometrics today include recognition by characteristic and by behaviour. Of these, face recognition is the most established with databases having evolved from small single shot single view databases, through multi-shot multi-view and on to current video-sequence databases. Results and potential of a new biometric are revealed primarily by the database on which new techniques are evaluated. Clearly, to ascertain the potential of gait as a biometric, a sequence-based database consisting of many subjects with multiple samples is needed. A large database enables the study of inter-subject variation. Further, issues concerning scene noise (or non-ideal conditions) need to be studied, ideally with a link between ground truth and application based analysis. Thus, we have designed and built a large human gait database, providing a large multi-purpose dataset enabling the investigation of gait as a biometric. In addition, it is also a useful database for many still and sequence based vision applications.

Automatic Recognition by Gait

Recognizing people by gait has a unique advantage over other biometrics: it has potential for use at a distance when other biometrics might be at too low a resolution, or might be obscured. The current state of the art can achieve over 90% identification rate under situations where the training and test data are captured under similar conditions, while recognition rates with change of clothing, shoe, surface, illumination, and pose usually decrease performance and are the subject of much of the current study. Recognition can be achieved on outdoor data with uncontrolled illumination and at a distance when other biometrics could not be used. We shall show how this position has been achieved, covering most approaches to recognition by gait and the databases on which performance has been evaluated. We shall describe the context of these approaches, show how recognition by gait can be achieved and how current limits on performance are understood. We shall describe results on the most popular database, showing how recognition can handle some of the covariates that can affect recognition. We shall also investigate the supporting literature for this research, since the notion that people can be recognized by gait has support not only in medicine and biomedicine, and also in literature and psychology and other areas. In this way, we shall show that this new biometric has capability and research and application potential in other domains

Using Gait as a Biometric, via Phase-weighted Magnitude Spectra

Gait is a biometric which is subject to increasing interest. Current approaches include modelling gait as a spatio-temporal sequence and as an articulated model. By considering legs only, gait can be considered to be the motion of interlinked pendula. We describe how the Hough transform is used to extract the lines which represent legs in sequences of video images. The change in inclination of these lines follows simple harmonic motion; this motion is used as the gait biometric. The method of least squares is used to smooth the data and to infill for missing points. Then, Fourier transform analysis is used to reveal the frequency components of the change in inclination of the legs. The transform data is then classified using the k-nearest neighbour rule. Experimental analysis shows how phase-weighted Fourier magnitude spectra afford an improved classification rate over use of just magnitude spectra. Accordingly, it appears that it is not just the frequency content which makes gait a practical biometric, but its phase as well.

Force Field Energy Functionals for Image Feature Extraction

The overall objective in defining feature space is to reduce the dimensionality of pattern space yet maintaining discriminatory power for classification and invariant description. To meet this objective, in the context of ear biometrics, a novel force field transformation has been developed in which the image is treated as an array of Gaussian attractors that act as the source of a force field. The directional properties of the force field are exploited to automatically locate the extrema of a small number of potential energy wells and associated potential channels. These form the basis of the ear description. This has been applied to a small database of ears and initial results show that the new approach has suitable performance attributes and shows promising results in automatic ear recognition.

What image information is important in silhouette-based gait recognition?

Gait recognition has recently gained significant attention, especially in vision-based automated human identification at a distance in visual surveillance and monitoring applications. Silhouette-based gait recognition is one of the most popular methods for recognising moving shapes. This paper aims to investigate the important features in silhouette-based gait recognition from point of view of statistical analysis. It is shown that the average silhouette includes a static component of gait (head and body) as the most important image part, while dynamic component of gait (swings of legs and arms) is ignored as the least important information. At the same time ignoring dynamic part of gait can result in loss in recognition rate in some cases, and the importance of better motion estimation is underlined.

Self-Calibrating View-Invariant Gait Biometrics

We present a new method for viewpoint independent gait biometrics. The system relies on a single camera, does not require camera calibration, and works with a wide range of camera views. This is achieved by a formulation where the gait is self-calibrating. These properties make the proposed method particularly suitable for identification by gait, where the advantages of completely unobtrusiveness, remoteness, and covertness of the biometric system preclude the availability of camera information and specific walking directions. The approach has been assessed for feature extraction and recognition capabilities on the SOTON gait database and then evaluated on a multiview database to establish recognition capability with respect to view invariance. Moreover, tests on the multiview CASIA-B database, composed of more than 2270 video sequences with 65 different subjects walking freely along different walking directions, have been performed. The obtained results show that human identification by gait can be achieved without any knowledge of internal or external camera parameters with a mean correct classification rate of 73.6% across all views using purely dynamic gait features. The performance of the proposed method is particularly encouraging for application in surveillance scenarios.

On using gait in forensic biometrics.

Abstract:  Given the continuing advances in gait biometrics, it appears prudent to investigate the translation of these techniques for forensic use. We address the question as to the confidence that might be given between any two such measurements. We use the locations of ankle, knee, and hip to derive a measure of the match between walking subjects in image sequences. The Instantaneous Posture Match algorithm, using Harr templates, kinematics, and anthropomorphic knowledge is used to determine their location. This is demonstrated using real CCTV recorded at Gatwick International Airport, laboratory images from the multiview CASIA‐B data set, and an example of real scene of crime video. To access the measurement confidence, we study the mean intra‐ and inter‐match scores as a function of database size. These measures converge to constant and separate values, indicating that the match measure derived from individual comparisons is considerably smaller than the average match measure from a population.