Gait recognition is a promising biometric technology for identification due to its non-invasiveness and long-distance. However, external variations such as clothing changes and viewpoint differences pose significant challenges to gait recognition. Silhouette-based methods preserve body shape but neglect internal structure information, while skeleton-based methods preserve structure information but omit appearance. To fully exploit the complementary nature of the two modalities, a novel triple branch gait recognition framework, TriGait, is proposed in this paper. It effectively integrates features from the skeleton and silhouette data in a hybrid fusion manner, including a two-stream network to extract static and motion features from appearance, a simple yet effective module named JSA-TC to capture dependencies between all joints, and a third branch for cross-modal learning by aligning and fusing low-level features of two modalities. Experimental results demonstrate the superiority and effectiveness of TriGait for gait recognition. The proposed method achieves a mean rank-1 accuracy of 96.0% over all conditions on CASIA-B dataset and 94.3% accuracy for CL, significantly outperforming all the state-of-the-art methods. The source code will be available at https://github.com/feng-xueling/TriGait/.

The paper provides a summary of the Competition on Human Identification at a Distance 2022 (HID 2022), which is the third one in a series of competitions. HID 2022 is for promoting the research in human identification at a distance by providing a benchmark to evaluate different methods. The competition attracted 112 valid registered teams. 71 teams and 51 teams submitted their results in the first phase and the second phase, respectively. Very encouraging results have been achieved, and the accuracies of the top teams are much higher than those achieved in the previous two competitions. In this paper, we introduce the competition including the dataset, experimental settings, competition organization, results from the top teams and their analysis. The methods used by the top teams are also presented in the paper. The progress of this competition can give us an optimistic view on gait recognition.

Recognising human attributes from surveillance footage is widely studied for attribute-based re-identification. However, most works assume coarse, expertly-defined categories, ineffective in describing challenging images. Such brittle representations are limited in descriminitive power and hamper the efficacy of learnt estimators. We aim to discover more relevant and precise subject descriptions, improving image retrieval and closing the semantic gap. Inspired by fine-grained and relative attributes, we introduce super-fine attributes, which now describe multiple, integral concepts of a single trait as multi-dimensional perceptual coordinates. Crowd prototyping facilitates efficient crowdsourcing of super-fine labels by pre-discovering salient perceptual concepts for prototype matching. We re-annotate gender, age and ethnicity traits from PETA, a highly diverse (19K instances, 8.7K identities) amalgamation of 10 re-id datasets including VIPER, CUHK and TownCentre. Employing joint attribute regression with the ResNet-152 CNN, we demonstrate substantially improved ranked retrieval performance with super-fine attributes in comparison to conventional binary labels, reporting up to a 11.2 and 14.8 percent mAP improvement for gender and age, further surpassed by ethnicity. We also find our 3 super-fine traits to outperform 35 binary attributes by 6.5 percent mAP for subject retrieval in a challenging zero-shot identification scenario.

This paper presents a feature selection model that aims to identify subjects from low-resolution surveillance images based on a soft biometric description query. The process is divided into three main stages. In the first stage, semantic segmentation is performed on the subjects, classifying and localising different parts of their bodies / accessories. The second stage extracts information from the segmentations and maps each subject to a vector in a soft biometric feature space. Last but not least, the purpose of the final stage is to find a good weighting on the features extracted in the previous step, based on the intuition that some of them are more important, more accurate or have a higher variance. It is assumed that the matching process might benefit considerably from a set of good weights. Analysis on the IEEE AVSS Challenge dataset shows encouraging performance for segmentation and subject matching with the correct subject reliably matched just outside the top ten on the training set, and just outside top 10% on the recently released test set.

In surveillance and security today it is a common goal to locate a subject of interest purely from a semantic description; think of an offender description form handed into a law enforcement agency. To date, these tasks are primarily undertaken by operators on the ground either by manually searching a premises or by combing through hours of video footage. Using computer vision to attempt to partially or fully automate these tasks has been gathering interest within the research community in recent years, however, to date there has been little coordinated effort to advance the field. This has motivated the challenge that is presented in this paper: the AVSS Challenge on Semantic Person Retrieval in Surveillance Using Soft Biometrics. This challenge consists of two related tasks: person re-identification from a semantic query and person search within a video from a query. In this paper, we present the publicly available data for this challenge, the evaluation framework, and the challenge results. It is our hope that the outcomes of this challenge and the availability of the data used in this challenge will expedite research and development in this societal field.

Many algorithms for semantic person retrieval suffer from a lack of training data often due to the difficulties in constructing a large dataset. We therefore propose a transfer learning based approach for semantic person identification and semantic person search. We apply the fine-tuned Mask R-CNN and DenseNet-161 for detection and attribute classification. The networks were pre-trained on the MS COCO and ILSVRC 2012 datasets. Our proposed approach achieves the highest recognition rate at each rank of CMC curve for semantic person identification and the highest average localization precision for semantic person search on our validation dataset.

In order to improve recognition performance, fusion has become a key technique in the recent years. Compared with single-mode biometrics, the recognition rate of multi-modal biometric systems is improved and the final decision is more confident. This paper introduces a novel joint density distribution based rank-score fusion strategy that combines rank and score information. Recognition at a distance has only recently been of interest in soft biometrics. We create a new soft biometric database containing the human face, body and clothing attributes at three different distances to investigate the influence by distance on soft biometric fusion. A comparative study about our method and other state of the art rank level and score level fusion methods are also conducted in this paper. The experiments are performed using a soft biometric database we created. The results demonstrate the recognition performance is significantly improved by our proposed method.

In some forms of gait analysis, it is important to be able to capture when the heel strikes occur. In addition, in terms of video analysis of gait, it is important to be able to localise the heel where it strikes on the floor. In this study, a new motion descriptor, acceleration flow , is introduced for detecting heel strikes. The key frame of heel strike can be determined by the quantity of acceleration flow within the region of interest, and positions of the strike can be found from the centre of rotation caused by radial acceleration. Our approach has been tested on a number of databases which were recorded indoors and outdoors with multiple views and walking directions for evaluating the detection rate under various environments. Experiments show the ability of our approach for both temporal detection and spatial positioning. The immunity of this new approach to three anticipated types of noises in real CCTV footage is also evaluated in our experiments. The authors acceleration flow detector is shown to be less sensitive to Gaussian white noise, whilst being effective with images of low‐resolution and with incomplete body position information when compared with other techniques.

The adverse visual conditions of surveillance environments and the need to identify humans at a distance have stimulated research in soft biometric attributes. These attributes can be used to describe a human's physical traits semantically and can be acquired without their cooperation. Soft biometrics can also be employed to retrieve identity from a database using verbal descriptions of suspects. In this paper, we explore unconstrained human face identification with semantic face attributes derived automatically from images. The process uses a deformable face model with keypoint localisation which is aligned with attributes derived from semantic descriptions. Our new framework exploits the semantic feature space to infer face signatures from images and bridges the semantic gap between humans and machines with respect to face attributes. We use an unconstrained dataset, LFW-MS4, consisting of all the subjects from view-1 of the LFW database that have four or more samples. Our new approach demonstrates that retrieval via estimated comparative facial soft biometrics yields a match in the top 10.23% of returned subjects. Furthermore, modelling of face image features in the semantic space can achieve an equal error rate of 12.71%. These results reveal the latent benefits of modelling visual facial features in a semantic space. Moreover, they highlight the potential of using images and verbal descriptions to generate comparative soft biometrics for subject identification and retrieval.

Recent expansion in surveillance systems has motivated research in soft biometrics that enable the unconstrained recognition of human faces. Comparative soft biometrics show superior recognition performance than categorical soft biometrics and have been the focus of several studies which have highlighted their ability for recognition and retrieval in constrained and unconstrained environments. These studies, however, only addressed face recognition for retrieval using human generated attributes, posing a question about the feasibility of automatically generating comparative labels from facial images. In this paper, we propose an approach for the automatic comparative labelling of facial soft biometrics. Furthermore, we investigate unconstrained human face recognition using these comparative soft biometrics in a human labelled gallery (and vice versa). Using a subset from the LFW dataset, our experiments show the efficacy of the automatic generation of comparative facial labels, highlighting the potential extensibility of the approach to other face recognition scenarios and larger ranges of attributes.

In this paper we introduce an algorithm for 3D motion estimation in point clouds that is based on Chasles' kinematic theorem. The proposed algorithm estimates 3D motion parameters directly from the data by exploiting the geometry of rigid transformation using an evidence gathering technique in a Hough-voting-like approach. The algorithm provides an alternative to the feature description and matching pipelines commonly used by numerous 3D object recognition and registration algorithms, as it does not involve keypoint detection and feature descriptor computation and matching. To the best of our knowledge, this is the first research to use kinematics theorems in an evidence gathering framework for motion estimation and surface matching without the use of any given correspondences. Moreover, we propose a method for voting for 3D motion parameters using a one-dimensional accumulator space, which enables voting for motion parameters more efficiently than other methods that use up to 7-dimensional accumulator spaces.

Automatically describing pedestrians in surveillance footage is crucial to facilitate human accessible solutions for suspect identification. We aim to identify pedestrians based solely on human description, by automatically retrieving semantic attributes from surveillance images, alleviating exhaustive label annotation. This work unites a deep learning solution with relative soft biometric labels, to accurately retrieve more discriminative image attributes. We propose a Semantic Retrieval Convolutional Neural Network to investigate automatic retrieval of three soft biometric modalities, across a number of `closed-world' and `open-world' re-identification scenarios. Findings suggest that relative-continuous labels are more accurately predicted than absolute-binary and relative-binary labels, improving semantic identification in every scenario. Furthermore, we demonstrate a top rank-1 improvement of 23.2% and 26.3% over a traditional, baseline retrieval approach, in one-shot and multi-shot re-identification scenarios respectively.

The need for faster feature matching has left as a result a new set of feature descriptors to the computer vision community, ORB, BRISK and FREAK amongst others. These new descriptors allow reduced time and memory consumption on the processing and storage stages, mitigating the implementation of more complex tasks. The problem is now the lack of fast interest point detectors with good repeatability to use with these new descriptors. A blob-detection algorithm was recently presented that uses an innovative non-deterministic low-level operator called the Brightness Clustering Transform (BCT) (Lomeli-R. and Nixon in The brightness clustering transform and locally contrasting keypoints. In CAIP. Springer, Berlin, pp 362–373, 2015). This algorithm is easy to implement and is faster than most of the currently used feature detectors. The BCT can be thought as a coarse-to-fine search through scale spaces for the true derivative of the image. The new algorithm is called Locally Contrasting Keypoints detector (LOCKY). Showing good robustness to image transformations included in the Oxford affine-covariant regions dataset, LOCKY is amongst the fastest affine-covariant feature detectors. In this paper, we present an extension of the BCT that detects larger structures maintaining timing and repeatability; this extension is called the BCT-S.

Soft biometrics have increasingly attracted research interest and are often considered as major cues for identity, especially in the absence of valid traditional biometrics, as in surveillance. In everyday life, several incidents and forensic scenarios highlight the usefulness and capability of identity information that can be deduced from clothing. Semantic clothing attributes have recently been introduced as a new form of soft biometrics. Although clothing traits can be naturally described and compared by humans for operable and successful use, it is desirable to exploit computer vision to enrich clothing descriptions with more objective and discriminative information. This allows automatic extraction and semantic description and comparison of visually detectable clothing traits in a manner similar to recognition by eyewitness statements. This paper proposes a novel set of soft clothing attributes, described using small groups of high-level semantic labels, and automatically extracted using computer-vision techniques. In this way, we can explore the capability of human attributes vis-a-vis those which are inferred automatically by computer vision. Categorical and comparative soft clothing traits are derived and used for identification/re-identification either to supplement soft body traits or to be used alone. The automatically and manually derived soft clothing biometrics are employed in challenging invariant person retrieval. The experimental results highlight promising potential for use in various applications.

We describe how image analysis can be used to detect the presence of Alzheimer's disease. The data are images of brain tissue collected from subjects with and without Alzheimer's disease. The analysis concentrates on the shape and structure of the blood vessels which are known to be affected by amyloid beta, whose drainage is affected by Alzheimer's disease. The structure is analysed by a new approach which measures the Influence of the blood vessels' branching structures. Their density and tortuosity are analysed in conjunction with a boundary description derived using Fourier descriptors. These measures form a feature vector which is derived from the images of brain tissue, and the discrimination capability shows that it is possible to detect the presence of Alzheimer's disease using these measures and in an automated way. These measures also show that shape information is influenced by the vessels' branching structure, as known to be consistent with Alzheimer's disease evolution.

Recently, soft biometrics has emerged as a novel attribute-based person description for identification. It is likely that soft biometrics can be deployed where other biometrics cannot, and have stronger invariance properties than vision-based biometrics, such as invariance to illumination and contrast. Previously, a variety of bodily soft biometrics has been used for identifying people. Describing a person by their clothing properties is a natural task performed by people. As yet, clothing descriptions have attracted little attention for identification purposes. There has been some usage of clothing attributes to augment biometric description, but a detailed description has yet to be used. We show here how clothing traits can be exploited for identification purposes. We explore the validity and usability of a set of proposed semantic attributes. Human identification is performed, evaluated and compared using different proposed forms of soft clothing traits in addition and in isolation.

Much progress has been made recently in the development of 3D acquisition technologies, which increased the availability of low-cost 3D sensors, such as the Microsoft Kinect. This promotes a wide variety of computer vision applications needing object recognition and 3D reconstruction. We present a novel algorithm for full 3D reconstruction of unknown rotating objects in 2.5D point cloud sequences, such as those generated by 3D sensors. Our algorithm incorporates structural and temporal motion information to build 3D models of moving objects and is based on motion compensated temporal accumulation. The proposed algorithm requires only the fixed centre or axis of rotation, unlike other 3D reconstruction methods, it does not require key point detection, feature description, correspondence matching, provided object models or any geometric information about the object. Moreover, our algorithm integrally estimates the best rigid transformation parameters for registration, applies surface resembling, reduces noise and estimates the optimum angular velocity of the rotating object.

It has been recently shown that preclinical analysis of computed tomography 3D image volumes can provide essential information to find the optimal position of an implant in hip replacement procedures. In order to extract such data, proper segmentation is crucial. Many of the currently-available methods depend on manually segmented data as the first step. Inherent difficulties concern the similar density of adjacent structures, and that physically-separated structures appear to touch in scanned imagery. In this study, we describe a new technique based on pressure analogy that depends on the local features of the image to accurately and automatically segment and visualize the femur bone and separate it from the acetabulum. The Dice coefficient was employed to study the similarity between the surface area of the segmentations compared with the manually segmented data, and a high value has been achieved. The same method also showed promising results in segmenting other limbs such as the pelvis, tibia and fibula bones.

Soft biometrics are a new form of biometric identification which use physical or behavioral traits that can be naturally described by humans. Unlike other biometric approaches, this allows identification based solely on verbal descriptions, bridging the semantic gap between biometrics and human description. To permit soft biometric identification the description must be accurate, yet conventional human descriptions comprising of absolute labels and estimations are often unreliable. A novel method of obtaining human descriptions will be introduced which utilizes comparative categorical labels to describe differences between subjects. This innovative approach has been shown to address many problems associated with absolute categorical labels-most critically, the descriptions contain more objective information and have increased discriminatory capabilities. Relative measurements of the subjects' traits can be inferred from comparative human descriptions using the Elo rating system. The resulting soft biometric signatures have been demonstrated to be robust and allow accurate recognition of subjects. Relative measurements can also be obtained from other forms of human representation. This is demonstrated using a support vector machine to determine relative measurements from gait biometric signatures-allowing retrieval of subjects from video footage by using human comparisons, bridging the semantic gap.

Soft biometric information extracted from a human body (e.g., height, gender, skin color, hair color, and so on) is ancillary information easily distinguished at a distance but it is not fully distinctive by itself in recognition tasks. However, this soft information can be explicitly fused with biometric recognition systems to improve the overall recognition when confronting high variability conditions. One significant example is visual surveillance, where face images are usually captured in poor quality conditions with high variability and automatic face recognition systems do not work properly. In this scenario, the soft biometric information can provide very valuable information for person recognition. This paper presents an experimental study of the benefits of soft biometric labels as ancillary information based on the description of human physical features to improve challenging person recognition scenarios at a distance. In addition, we analyze the available soft biometric information in scenarios of varying distance between camera and subject. Experimental results based on the Southampton multibiometric tunnel database show that the use of soft biometric traits is able to improve the performance of face recognition based on sparse representation on real and ideal scenarios by adaptive fusion rules.

Summary form only given. The prime advantage of gait as a biometric is that it can be used for recognition at a distance whereas other biometrics cannot. There is a rich selection of approaches and many advances have been made, as will be reviewed in this talk. Soft biometrics is an emerging area of interest in biometrics where we augment computer vision derived measures by human descriptions. Applied to gait biometrics, this again can be used where other biometric data is obscured or at too low resolution. The human descriptions are semantic and are a set of labels which are converted into numbers. Naturally, there are considerations of language and psychology when the labels are collected. After describing current progress in gait biometrics, this talk will describe how the soft biometrics labels are collected, and how they can be used to enhance recognising people by the way they walk. As well as reinforcing biometrics, this approach might lead to a new procedure for collecting witness statements, and to the ability to retrieve subjects from video using witness statements.

We argue for the importance of explicit semantic modelling in human-centred texture analysis tasks such as retrieval, annotation, synthesis, and zero-shot learning. To this end, low-level attributes are selected and used to define a semantic space for texture. 319 texture classes varying in illumination and rotation are positioned within this semantic space using a pair wise relative comparison procedure. Low-level visual features used by existing texture descriptors are then assessed in terms of their correspondence to the semantic space. Textures with strong presence of attributes connoting randomness and complexity are shown to be poorly modelled by existing descriptors. In a retrieval experiment semantic descriptors are shown to outperform visual descriptors. Semantic modelling of texture is thus shown to provide considerable value in both feature selection and in analysis tasks.

Visual surveillance finds increasing deployment for monitoring urban environments. Operators need to be able to determine identity from surveillance images and often use face recognition for this purpose. In surveillance environments, it is necessary to handle pose variation of the human head, low frame rate, and low resolution input images. We describe the first use of gait to enable face acquisition and recognition, by analysis of 3-D head motion and gait trajectory, with super-resolution analysis. We use region- and distance-based refinement of head pose estimation. We develop a direct mapping to relate the 2-D image with a 3-D model. In gait trajectory analysis, we model the looming effect so as to obtain the correct face region. Based on head position and the gait trajectory, we can reconstruct high-quality frontal face images which are demonstrated to be suitable for face recognition. The contributions of this research include the construction of a 3-D model for pose estimation from planar imagery and the first use of gait information to enhance the face extraction process allowing for deployment in surveillance scenarios.

Many studies have shown that it is possible to recognize people by the way they walk. However, there are a number of covariate factors that affect recognition performance. The time between capturing the gallery and the probe has been reported to affect recognition the most. To date, no study has isolated the effect of time, irrespective of other covariates. Here, we present the first principled study that examines the effect of elapsed time on gait recognition. Using empirical evidence we show for the first time that elapsed time does not affect recognition significantly in the short-medium term. This finding challenges the existing view in the literature that time significantly affects gait recognition. We employ existing gait representations on a novel dataset captured specifically for this study. By controlling the clothing worn by the subjects and the environment, a Correct Classification Rate (CCR) of 95% has been achieved over the longest time period yet considered for gait on the largest ever temporal dataset. Our results show that gait can be used as a reliable biometric over time and at a distance if we were able to control all other factors such as clothing, footwear etc. We have also investigated the effect of different type of clothes, variations in speed and footwear on the recognition performance. The purpose of these experiments is to provide an indication of why previous studies (employing the same techniques as this study) have achieved significantly lower recognition performance over time. Our experimental results show that clothing and other covariates have been confused with elapsed time previously in the literature. We have demonstrated that clothing drastically affects the recognition performance regardless of elapsed time and significantly more than any of the other covariates that we have considered here.

There have as yet been few gait biometrics approaches which use temporal 3D data. Clearly, 3D gait data conveys more information than 2D data and it is also the natural representation of human gait perceived by human. In this paper we explore the potential of using model-based methods in a 3D volumetric (voxel) gait dataset. We use a structural model including articulated cylinders with 3D Degrees of Freedom (DoF) at each joint to model the human lower legs. We develop a simple yet effective model-fitting algorithm using this gait model, correlation filter and a dynamic programming approach. Human gait kinematics trajectories are then extracted by fitting the gait model into the gait data. At each frame we generate a correlation energy map between the gait model and the data. Dynamic programming is used to extract the gait kinematics trajectories by selecting the most likely path in the whole sequence. We are successfully able to extract both gait structural and dynamics features. Some of the features extracted here are inherently unique to 3D data. Analysis on a database of 46 subjects each with 4 sample sequences, shows an encouraging correct classification rate and suggests that 3D features can contribute even more.

We present an experimental study to demonstrate the effect of the time difference in image acquisition for gallery and probe on the performance of ear recognition. This experimental research is the first study on the time effect on ear biometrics. For the purpose of recognition, we convolve banana wavelets with an ear image and then apply local binary pattern on the convolved image. The histograms of the produced image are then used as features to describe an ear. A histogram intersection technique is then applied on the histograms of two ears to measure the ear similarity for the recognition purposes. We also use analysis of variance (ANOVA) to select features to identify the best banana wavelets for the recognition process. The experimental results show that the recognition rate is only slightly reduced by time. The average recognition rate of 98.5% is achieved for an eleven month-difference between gallery and probe on an un-occluded ear dataset of 1491 images of ears selected from Southampton University ear database.

Soft biometrics is a new form of biometric identification which utilizes labeled physical or behavioral traits. Al though these traits intuitively have less discriminatory capability than mensurate approaches, they offer several ad vantages over traditional biometric techniques. Soft bio metric traits can be typically described as labels and measurements which can be understood by people, allowing retrieval and recognition based solely on human descriptions. Although being a key component of eyewitness evidence, conventional human descriptions can be considered to be unreliable. A novel method of obtaining human descriptions will be introduced which utilizes visual comparisons between subjects. The Elo rating system is used to infer relative measurements of subjects' traits based on the comparative human descriptions. This innovative approach to obtaining human descriptions has been shown to counter many problems associated with categorical (absolute) labels. The resulting soft biometric signatures have been demonstrated to be robust and allow accurate retrieval of subjects in video data and show that elapsed time can have little effect on comparative descriptions.

Abstract: There is a rich literature of approaches to image feature extraction in computer vision. Many sophisticated approaches exist for low- and high-level feature extraction but can be complex to implement with parameter choice guided by experimentation, but impeded by speed of computation. We have developed new ways to extract features based on notional use of physical paradigms, with parameterisation that is more familiar to a scientifically-trained user, aiming to make best use of computational resource. We describe how analogies based on gravitational force can be used for low-level analysis, whilst analogies of water flow and heat can be deployed to achieve high-level smooth shape detection. These new approaches to arbitrary shape extraction are compared with standard state-of-art approaches by curve evolution. There is no comparator operator to our use of gravitational force. We also aim to show that the implementation is consistent with the original motivations for these techniques and so contend that the exploration of physical paradigms offers a promising new avenue for new approaches to feature extraction in computer vision.

Recent work suggests that the human ear varies significantly between different subjects and can be used for identification. In principle, therefore, using ears in addition to the face within a recognition system could improve accuracy and robustness, particularly for non-frontal views. The paper describes work that investigates this hypothesis using an approach based on the construction of a 3D morphable model of the head and ear. One issue with creating a model that includes the ear is that existing training datasets contain noise and partial occlusion. Rather than exclude these regions manually, a classifier has been developed which automates this process. When combined with a robust registration algorithm the resulting system enables full head morphable models to be constructed efficiently using less constrained datasets. The algorithm has been evaluated using registration consistency, model coverage and minimalism metrics, which together demonstrate the accuracy of the approach. To make it easier to build on this work, the source code has been made available online.

We propose a learning method for gait synthesis from a sequence of shapes(frames) with the ability to extrapolate to novel data. It involves the application of PCA, first to reduce the data dimensionality to certain features, and second to model corresponding features derived from the training gait cycles as a Gaussian distribution. This approach transforms a non Gaussian shape deformation problem into a Gaussian one by considering features of entire gait cycles as vectors in a Gaussian space. We show that these features which we formulate as continuous functions can be modeled by PCA. We also use this model to in-between (generate intermediate unknown) shapes in the training cycle. Furthermore, this paper demonstrates that the derived features can be used in the identification of pedestrians.

In this paper, we explore a new approach for enriching the HoG method for pedestrian detection in an unconstrained outdoor environment. The proposed algorithm is based on using gait motion since the rhythmic footprint pattern for walking people is considered the stable and characteristic feature for the detection of walking people. The novelty of our approach is motivated by the latest research for people identification using gait. The experimental results confirmed the robustness of our method to enhance HoG to detect walking people as well as to discriminate between single walking subject, groups of people and vehicles with a detection rate of 100%. Furthermore, the results revealed the potential of our method to be used in visual surveillance systems for identity tracking over different camera views.

Ear recognition, as a biometric, has several advantages. In particular, ears can be measured remotely and are also relatively static in size and structure for each individual. Unfortunately, at present, good recognition rates require controlled conditions. For commercial use, these systems need to be much more robust. In particular, ears have to be recognized from different angles (poses), under different lighting conditions, and with different cameras. It must also be possible to distinguish ears from background clutter and identify them when partly occluded by hair, hats, or other objects. The purpose of this paper is to suggest how progress toward such robustness might be achieved through a technique that improves ear registration. The approach focuses on 2-D images, treating the ear as a planar surface that is registered to a gallery using a homography transform calculated from scale-invariant feature-transform feature matches. The feature matches reduce the gallery size and enable a precise ranking using a simple 2-D distance algorithm. Analysis on a range of data sets demonstrates the technique to be robust to background clutter, viewing angles up to ±13°, and up to 18% occlusion. In addition, recognition remains accurate with masked ear images as small as 20 × 35 pixels.

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.

The six articles in this special issue span a variety of topics in terms of gait representation and analysis for different applications.

We consider a sensor network placement problem where the sensing range of a sensor depends on its location in order to model the effect of terrain features. We study how sensors should be placed in order to maximize the coverage and illustrate how digital halftoning algorithms from the field of image processing can be useful in this respect. In particular, we reduce the sensor placement problem to a corresponding image halftoning problem and then apply two well known halftoning algorithms to the problem: dither mask halftoning and direct binary search. We illustrate our approach with experimental results and show that this approach is also applicable to the problem of preferential coverage.

Feature subset selection is an important preprocessing step for pattern recognition, to discard irrelevant and redundant information, as well as to identify the most important attributes. In this paper, we investigate a computationally efficient solution to select the most important features for gait recognition. The specific technique applied is based on mutual information (MI), which evaluates the statistical dependence between two random variables and has an established relation with the Bayes classification error. Extending our earlier research, we show that a sequential selection method based on MI can provide an effective solution for high-dimensional human gait data. To assess the performance of the approach, experiments are carried out based on a 73-dimensional model-based gait features set and on a 64 by 64 pixels model-free gait symmetry map on the Southampton HiD Gait database. The experimental results confirm the effectiveness of the method, removing about 50% of the model-based features and 95% of the symmetry map's pixels without significant loss in recognition capability, which outperforms correlation and analysis-of-variance-based methods.

Many studies have now shown that it is possible to recognize people by the way they walk. As yet there has been little formal study of the effects of covariates on the recognition process. We show how these factors can separately affect the walking pattern. Further we assess the contribution and discriminatory significance of the gait dynamics used for recognition. Based on a covariate-based probe dataset of 440 samples, a high recognition rate of 73.4% is achieved using the KNN classifier. This is to confirm that people identification using dynamic gait features is still perceivable with better recognition rate even under the different covariate factors.

We present a new method for viewpoint independent markerless gait analysis. The system uses a single camera, does not require camera calibration and works with a wide range of directions of walking. 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 use of marker based technology. Tests on more than 200 video sequences with subjects walking freely along different walking directions have been performed. The obtained results show that markerless gait analysis can be achieved without any knowledge of internal or external camera parameters and that the obtained data that can be used for gait biometrics purposes. The performance of the proposed method is particularly encouraging for its appliance in surveillance scenarios.

Ears are a new biometric with major advantage in that they appear to maintain their structure with increasing age. Expanding on our previous parts-based model, we propose a new wavelet approach. In this, the log-Gabor filter exploits the frequency content of the ear boundary curves. Extending our model description, a specific aim of the new approach is to capture information in the ear¿s outer structures. Ear biometrics is also concerned with the effects of partial occlusion, mostly by hair and earrings. By localization, intuitively a wavelet can offer performance advantage when handling occluded data. We also add a more robust matching strategy to restrict the influence of erroneous wavelet coefficients. Significant improvement is observed when we combine the model and the log-Gabor filter, and we will show that this improvement is maintained as the ears get occluded.

Many studies have now shown that it is possible to recognize people by the way they walk. As yet there has been little formal study of people recognition using the kinematic-related gait features. We present a new method for gait recognition using dynamic features including the angular measurements of the lower limbs as well as the spatial displacement of the trunk. Gait signatures are derived using a feature selection algorithm which is based on a validation-criterion. We show that gait angular measurements derived from the joint motions mainly the ankle, knee and hip angles, possess most of the discriminatory potency for gait recognition with an achieved correct classification rate of 95.7%.

AREA 2008 is the first ACM international workshop on analysis and retrieval of events, actions and workflows in video streams. Such research is nowadays critical for many real-life applications, such as area supervision, semantic characterization and annotation of video streams, quality assurance, and security. This workshop consists of 16 high quality papers organized in four thematic sessions. More specifically, the first session is dedicated to new objects tracking algorithms under complex environments and to object labeling techniques. The second session deals with methods, tools and architectures for detecting high level semantics (events, actions, and workflows) in video sequences. The third session presents new algorithms for analyzing video sequences oriented to detecting humans' actions or implicitly annotating multimedia content. Finally, the fourth includes a special session of the recent advantages of the ongoing research projects in the field of multimedia analysis, cognitive video supervision, personalized video annotation, fast retrieval of multimedia content in compressed domain and scheduling tools for interactive multimedia services. We hope that these proceedings will serve as a valuable reference for analysis of events in video streams.

The development of large scale biometric systems requires experiments to be performed on large amounts of data. Existing capture systems are designed for fixed experiments and are not easily scalable. In this scenario even the addition of extra data is difficult. We developed a prototype biometric tunnel for the capture of non-contact biometrics. It is self contained and autonomous. Such a configuration is ideal for building access or deployment in secure environments. The tunnel captures cropped images of the subject's face and performs a 3D reconstruction of the person's motion which is used to extract gait information. Interaction between the various parts of the system is performed via the use of an agent framework. The design of this system is a trade-off between parallel and serial processing due to various hardware bottlenecks. When tested on a small population the extracted features have been shown to be potent for recognition. We currently achieve a moderate throughput of approximate 15 subjects an hour and hope to improve this in the future as the prototype becomes more complete

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

Large arrays of cameras are increasingly being employed for producing high quality image sequences needed for motion analysis research. This leads to the logistical problem with coordination and control of a large number of cameras. In this paper, we used a lightweight multi-agent system for coordinating such camera arrays. The agent framework provides more than a remote sensor access API. It allows reconfigurable and transparent access to cameras, as well as software agents capable of intelligent processing. Furthermore, it eases maintenance by encouraging code reuse. Additionally, our agent system includes an automatic discovery mechanism at startup, and multiple language bindings. Performance tests showed the lightweight nature of the framework while validating its correctness and scalability. Two different camera agents were implemented to provide access to a large array of distributed cameras. Correct operation of these camera agents was confirmed via several image processing agents.

Phase congruency is a new method for detecting features in images. One of its significant strengths is its invariance to lighting variation within an image, as well as being able to detect a wide range of interesting features. We present a method for estimating the phase congruency of localised frequencies that cannot be measured separately by Gabor filters. We show that by measuring the ratio of the standard deviation to the mean energy between different phase shifted Gabor filters we are able to estimate whether the localised frequencies are phase congruent. We then show example results from applying this estimation procedure to a set of images. We also show improvements when compared to another phase congruency detector. We conclude that the concept of estimating the phase congruency of localised features is possible, but more work is needed to mature the technique to a robust feature detector.

Abstract We develop a new automated markerless motion capture system for the analysis of walking people. We employ global evidence gathering techniques guided by biomechanical analysis to robustly extract articulated motion. This forms a basis for new deformable contour models, using local image cues to capture shape and motion at a more detailed level. We extend the greedy snake formulation to include temporal constraints and occlusion modelling, increasing the capability of this technique when dealing with cluttered and self‐occluding extraction targets. This approach is evaluated on a large database of indoor and outdoor video data, demonstrating fast and autonomous motion capture for walking people. Copyright © 2004 John Wiley & Sons, Ltd.

Low back pain is a significant problem in the industrialized world. Diagnosis of the underlying causes can be extremely difficult. Since mechanical factors often play an important role, it can be helpful to study the motion of the spine. Digital videofluoroscopy has been developed for this study and it can provide image sequences with many frames, but which often suffer due to noise, exacerbated by the very low radiation dosage. Thus, determining vertebra position within the image sequence presents a considerable challenge. There have been many studies on vertebral image extraction, but problems of repeatability, occlusion and out-of-plane motion persist. In this paper, we show how the Hough transform (HT) can be used to solve these problems. Here, Fourier descriptors were used to describe the vertebral body shape. This description was incorporated within our HT algorithm from which we can obtain affine transform parameters, i.e., scale, rotation and center position. The method has been applied to images of a calibration model and to images from two sequences of moving human lumbar spines. The results show promise and potential for object extraction from poor quality images and that models of spinal movement can indeed be derived for clinical application.

Foreground/background segmentation is an active research area for moving object analysis. We combine two probabilistic approaches one of which estimates foreground/background probabilistic density and the other uses prior knowledge to decompose the colour space. The observed performance advantages are associated with the fusion of operators with completely different basis. Tests on outdoor and indoor sequences confirm the efficacy of this approach. The new algorithms can successfully identify and remove shadows and highlights with improved moving-object segmentation. A particular advantage of our evaluation is that it is the first approach that compares foreground/background labelling with results obtained from labelling by broadcast techniques. 1

Land cover class composition of remotely sensed image pixels can be estimated using soft classification techniques increasingly available in many GIS packages. However, their output provides no indication of how such classes are distributed spatially within the instantaneous field of view represented by the pixel. Techniques that attempt to provide an improved spatial representation of land cover have been developed, but not tested on the difficult task of mapping from real satellite imagery. The authors investigated the use of a Hopfield neural network technique to map the spatial distributions of classes reliably using information of pixel composition determined from soft classification previously. The approach involved designing the energy function to produce a ‘best guess’ prediction of the spatial distribution of class components in each pixel. In previous studies, the authors described the application of the technique to target identification, pattern prediction and land cover mapping at the sub-pixel scale, but only for simulated imagery. We now show how the approach can be applied to Landsat Thematic Mapper (TM) agriculture imagery to derive accurate estimates of land cover and reduce the uncertainty inherent in such imagery. The technique was applied to Landsat TM imagery of small-scale agriculture in Greece and largescale agriculture near Leicester, UK. The resultant maps provided an accurate and improved representation of the land covers studied, with RMS errors for the Landsat imagery of the order of 0.1 in the new fine resolution map recorded. The results showed that the neural network represents a simple efficient tool for mapping land cover from operational satellite sensor imagery and can deliver requisite results and improvements over traditional techniques for the GIS analysis of practical remotely sensed imagery at the sub pixel scale.

We describe a new method for automatic gait recognition based on analysing the symmetry of human motion using the Generalised Symmetry Operator. This approach is reinforced by the psychologists’ view that gait is a symmetrical pattern of motion and results show that gait can indeed be recognised by symmetry analysis.

Recent research using statistical moments to describe moving shapes through an image sequence has led to an interest in reconstructing moving shapes from their moment description. This paper discusses how the moment description through a series of frames might be used to predict missing or intermediate frames within a sequence. Additionally, this highlights generic aspects of moment reconstruction which rarely receive more than scant attention. The ideas presented use Zernike moments, although the general framework is applicable to all types of moments. We show how a moving human silhouette can be reconstructed with accuracy by interpolation from a moment history. 1

We describe a new method for analyzing and extracting human gait motion by combining statistical methods with image processing. The periodic motion of human gait is modeled by trigonometric-polynomial interpolant functions. The gait description is derived by topological analysis guided by medical studies that selects areas from which joint angles are derived by regression analysis. Then, the interpolant functions are fitted to the gait data and whilst showing fidelity to earlier medical studies, also show recognition capability. As such, a new combination of medical knowledge, image processing and regression analysis can be used to label human motion in image sequences.

Gait is a new biometric aimed to recognise a subject by the manner in which they walk. Gait has several advantages over other biometrics, most notably that it is non-invasive and perceivable at a distance when other biometrics are obscured. We present a new area based metric, called gait masks, which provides statistical data intimately related to the gait of the subject and motivated by medical studies. This provides the first statistical approach that can expose the dynamics of the change in area of a subject. Early results show promising results with a recognition rate of 90% on a standard database. Further, there appear to be performance advantages with respect to handling of noise associated with this new approach, together with capability for extension and generalisation. Future research will capitalise on the advantages of this new approach, together with analysis on a larger database. 1.

New Zernike velocity moments have been developed to describe an object, not only by its shape , but also by its motion throughout an image sequence. These are

We show how the symmetry of motion can be extracted by using the generalised symmetry operator for analysing motion and for gait recognition. This operator, rather than relying on the borders of a shape or on general appearance, locates features by their symmetrical properties. This approach is reinforced by the view from psychology that human gait is a symmetrical pattern of motion, and by other works. We applied our new method to compare animal gait, and for recognition by gait. Results show that the symmetry properties of gait appear to be unique and can indeed be used for analysis and for recognition. We have so far achieved promising recognition rates of over 95%. Performance analysis also suggests that symmetry enjoys practical advantages such as relative immunity to noise with capability to handle occlusion and as such might prove suitable for applications like clip-database browsing.

Fuzzy classification techniques have been developed recently to estimate the class composition of image pixels, but their output provides no indication of how these classes are distributed spatially within the instantaneous field of view represented by the pixel. As such, while the accuracy of land cover target identification has been improved using fuzzy classification, it remains for robust techniques that provide better spatial representation of land cover to be developed. Such techniques could provide more accurate land cover metrics for determining social or environmental policy, for example. The use of a Hopfield neural network to map the spatial distribution of classes more reliably using prior information of pixel composition determined from fuzzy classification was investigated. An approach was adopted that used the output from a fuzzy classification to constrain a Hopfield neural network formulated as an energy minimization tool. The network converges to a minimum of an energy function, defined as a goal and several constraints. Extracting the spatial distribution of target class components within each pixel was, therefore, formulated as a constraint satisfaction problem with an optimal solution determined by the minimum of the energy function. This energy minimum represents a "best guess" map of the spatial distribution of class components in each pixel. The technique was applied to both synthetic and simulated Landsat TM imagery, and the resultant maps provided an accurate and improved representation of the land covers studied, with root mean square errors (RMSEs) for Landsat imagery of the order of 0.09 pixels in the new fine resolution image recorded.

The objective in defining feature space is to reduce the dimension of the original pattern space yet maintaining discriminatory power for classification. To meet this objective in the context of ear and face 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 a small number of potential energy wells and channels that form the basis of a characteristic feature vector. Here, we generalise the analysis, and the stock of applications.

Two recent approaches are combined in a new technique to find moving arbitrary shapes. We combine the Velocity Hough Transform, which extracts moving conic sections, with a continuous formulation for arbitrary shape extraction, which avoids discretisation errors associated with GHT methods. The new approach has been evaluated on synthetic and real imagery and is demonstrated to provide motion analysis that is resilient to noise and to be able to detect its target shapes, which are both moving and arbitrary. Further, it is shown to have performance advantages over contemporaneous single-image extraction techniques. Finally, it appears to offer improved immunity to noise and occlusion, consistent with evidence gathering techniques, as shown by results on real images. 1

The overall objective in de®ning feature space is to reduce the dimensionality of pattern space yet maintaining discriminatory power for classi®cation and invariant description.To meet this objective, in the context of ear biometrics, a novel force ®eld transformation has been developed in which the image is treated as an array of Gaussian attractors that act as the source of a force ®eld.The directional properties of the force ®eld 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.

The generalized symmetry operator extracts image features by accumulating evidence based on spatial and directional edge constraints. A novel extension enables local focus to improve discriminatory ability in the symmetry functional. Results on simulated and real imagery confirm this new capability.

To recognize people by their gait from a sequence of images, we have proposed a statistical approach which combined eigenspace transformation (EST) with canonical space transformation (CST) for feature transformation of spatial templates. This approach is used to reduce data dimensionality and to optimize the class separability of different gait sequences simultaneously. Good recognition rates have been achieved. Here, we incorporate temporal information from optical flows into three kinds of temporal templates and use them as features for gait recognition in addition to the spatial templates. The recognition performance for four kinds of template features has been evaluated in this paper. Experimental results show that spatial templates, horizontal-flow templates and the combined horizontal-flow and vertical-flow templates are better than vertical-flow templates for gait recognition. 1 Introduction Biometrics such as automatic face and voice recognition continue to be sub...

We present a new evidence gathering based approach, aimed to extract moving articulated objects from a temporal sequence of images. The new technique is designed to enable the automated determination of parameters pertaining to human gait, with a view to possible use as a biometric for recognition purposes. The articulated line feature extraction technique, uses a genetic algorithm (GA) based implementation of the Velocity Hough Transform (VHT). Using a GA to perform a heuristic search of the parameter space, rather than an exhaustive one, overcomes the problems of computation time and memory requirements associated with the original approach. The new technique employs a parametric gait model consisting of a pair of articulated lines, jointed at the hip. Trials on real image sequences of pedestrians demonstrate that the approach is capable of locating and tracking a walking subject. Moreover, the technique is able to provide reasonable estimates of an individual’s gait cycle period and hip rotation patterns, which are pertinent to recognition. However, current levels of accuracy are insufficient for these purposes. Nevertheless, the results demonstrate that the articulated line feature extraction technique has potential for use as an automated gaitdata retrieval system. 1

In this paper, we propose a new approach which combines canonical space transformation (CST) with the eigenspace transformation (EST) for feature extraction of temporal templates in a gait sequence. Eigenspace transformation has been demonstrated to be a potent metric in automatic face recognition and gait analysis, but without using data analysis to increase classification capability. Our method can be used to reduce data dimensionality and to optimize the class separability of different gait sequences simultaneously. Each temporal template is projected from high-dimensional image space to a single point in low-dimensional canonical space. In this new space the recognition of human gait by template matching becomes much faster and simpler. Experimental results for human gait analysis show this method is superior to eigenspace representation. As such, the combination of EST and CST is shown to be of considerable advantage in an emerging new biometric.

Video-rate three-dimensional (3-D) acquisition is desirable, in particular for capturing the mouth's shape when modeling the vocal tract. In a new structured light technique, scenes are illuminated by an array of circular spots which are color encoded to resolve spatial ambiguity. The position and shape of the imaged spots depend on the location and orientation of the illuminated 3-D surface. We present a novel 3-D Hough transform (HT) to detect 3-D surface location and orientation via the imaged spots, with voting constraints applied to maximize potential accuracy. This new technique is demonstrated to successfully extract the 3-D data for a moving face from images acquired at video-rate.

We propose a new dynamic feature extraction technique for the analysis of temporal image sequences. Based on the Hough transform, the new technique includes motion in the evidence gathering process to detect moving parametric shapes. Experimental results on real and synthetic image sequences show that this new technique offers increased noise immunity and improves performance, especially in cases of partial occlusion. The new technique is extended to enable the identification of features exhibiting a time variant structure and applied to the task of extracting arterial wall data from a sequence of cross-sectional ultrasound images. Experimental results demonstrate that the approach can provide good results and highlights the performance of the new technique in noisy environments.

A conventional active contour formulation suffers difficulty in appropriate choice of an initial contour and values of parameters. Recent approaches have aimed to resolve these problems but can compromise other performance aspects. To relieve the problem in initialization, we use a dual active contour, which is combined with a local shape model to improve the parameterization. One contour expands from inside the target feature, the other contracts from the outside. The two contours are interlinked to provide a balanced technique with an ability to reject "weak" local energy minima.

The generalised Hough transform extracts arbitrary objects by using a non-analytic model shape representation obtained from gradient direction information. The main drawback of this technique is the excessive computational burden because of the four-dimensional parameter space required when orientation and scale are unknown. We present a novel representation of a model shape defined by the geometric relationship given by the position of a collection of edge points. This representation avoids errors due to unreliable gradient direction information and is used to reduce the computational requirements by decomposing the four-dimensional parameter space into two two-dimensional sub-spaces. Experimental results show the efficacy of the new technique for extracting shapes from synthetic and real images.

The statistical geometric features (SGF) are a new approach to texture analysis combining statistics with geometrical attributes to give a powerful discriminatory ability. The original scheme considered the approach in principal and did not address factors important to its eventual application, namely its implementation and the segmentation of texture imagery. We show how the implementation factors can affect performance and how it can be used for segmentation. Using SGF, a new adaptively-positioned windowing strategy for segmentation delivers a performance which, in terms of speed and accuracy, gives a performance between the traditional tiled- and sliding-window approaches.

In this paper we present a novel formulation for the extraction of arbitrary shapes in model-based recognition. The formulation is based on the mapping defined in the Hough transform. We develop this mapping for the analytic representation of a shape characterised by a Fourier parameterisation. Edge direction information is included in the formulation as a way of reducing the computational requirements in the extraction process. The proposed approach extends the analytic formulation of the Hough transform to arbitrary shapes. An analytic representation provides a compact and extensive coverage of a shape which leads to an accurate and efficient evidence accumulation process. Experimental results show that the new approach can handle noise and occlusion in synthetic and real images.

Snakes are now a very popular technique for shape extraction by minimising a suitably formulated energy functional. A dual snake configuration using dynamic programming has been developed to locate a global energy minimum. This complements recent approaches to global energy minimisation via simulated annealing and genetic algorithms. These differ from a conventional evolutionary snake approach, where an energy function is minimised according to a local optimisation strategy and may not converge to extract the target shape, in contrast with the guaranteed convergence of a global approach. The new technique employing dynamic programming is deployed to extract the inner face boundary, along with a conventional normal-driven technique to extract the outer face boundary. Application to a database of 75 subjects showed that the outer contour was extracted successfully for 96% of the subjects and the inner contour was successful for 82%. The results demonstrated the benefits that could accrue from inclusion of face features, giving an appropriate avenue for future research.

Describes a new fully motion-adaptive spatio-temporal filtering technique to reduce the speckle in ultrasound images. The advantages of this approach are demonstrated in echocardiographic boundary detection and in comparison with other techniques. The first stage of many automated echocardiographic image interpretation schemes is filtering to reduce the amount of speckle noise. The authors show how the two-dimensional least mean squares (TDLMS) filter can be configured as a motion-compensated filter for a time sequence of ultrasound images that eliminates the blurring associated with direct averaging. For an image corrupted by multiplicative speckle noise, the mode of the intensity distribution approximates the maximum likelihood estimator. In consequence, the temporal filter's output is biased towards the mode from the mean, using information contained within the speckle itself. A new adaptive algorithm for controlling the filter's convergence is also included. To evaluate performance, application to simulated, phantom, and an in vivo test sequence of the carotid artery are considered in comparison with other techniques. The effect of filtering on edges is of great importance, as these are used by subsequent image interpretation schemes. Quantitative measurements demonstrate the effectiveness of the Biased TDLMS filter, for both noise reduction and edge preservation. Echocardiographic images have a high noise content and suffer from poor contrast. Despite this challenging environment, the Biased TDLMS filter is shown to produce images that are better inputs for subsequent feature extraction. The benefits for echocardiographic images are highlighted by considering the problems of mitral valve analysis and extraction of the left atrium boundary.

Many features can be used to describe a human face but few have been used in combination. Extending the feature vector using orthogonal sets of measurements can reduce the variance of a matching measure, to improve discrimination capability. This paper investigates how different features can be used for discrimination, alone or when integrated into an extended feature vector. This study concentrates on improving feature definition and extraction from a frontal view image, incorporating and extending established measurements. These form an extended feature vector based on four feature sets: geometric (distance) measurements, the eye region, the outline contour, and the profile. The profile, contour, and eye region are described by the Walsh power spectrum, normalized Fourier descriptors, and normalized moments, respectively. Although there is some correlation between the geometrical measures and the other sets, their bases (distance, shape description, sequency, and statistics) are orthogonal and hence appropriate for this research. A database of face images was analyzed using two matching measures which were developed to control differently the contributions of elements of the feature sets. The match was evaluated for both measures for the separate feature sets and for the extended feature vector. Results demonstrated that no feature set alone was sufficient for recognition whereas the extended feature vector could discriminate between subjects successfully.

Active contours are now established as a technique for extracting salient contours from an image. Unfortunately the original technique suffers from many problems. A novel model-based dual active contour, a method of integrating global shape information with two active contours, has been developed to overcome the primary problems; sensitivity to initialisation and undesirable attractions by insignificant localised or regionalised features. The model guides the technique to avoid insignificant minima and is relinquished when the energy minimum is sufficiently compatible. The technique then finally operates as a pair of conventional active contours, ensuring that only image information is extracted, consistent with the original technique. 1

This paper presents a new texture feature set based on the statistics of geometrical attributes of connected regions in a stack of binary images obtained from a texture image. Systematic evaluation using all the Brodatz textures shows that the new set outperforms the well-known statistical gray level dependence matrix, the recently proposed statistical feature matrix, and Liu's features.>