An end-to-end exemplar association for unsupervised person Re-identification.

Tracklet association methods learn the cross camera retrieval ability though associating underlying cross camera positive samples, which have proven to be successful in unsupervised person re-identification task. However, most of them use poor-efficiency association strategies which costs long training hours but gains the low performance. To solve this, we propose an effective end-to-end exemplar associations (EEA) framework in this work. EEA mainly adapts three strategies to improve efficiency: (1) end-to-end exemplar-based training, (2) exemplar association and (3) dynamic selection threshold. The first one is to accelerate the training process, while the others aim to improve the tracklet association precision. Compared with existing tracklet associating methods, EEA obviously reduces the training cost and achieves the higher performance. Extensive experiments and ablation studies on seven RE-ID datasets demonstrate the superiority of the proposed EEA over most state-of-the-art unsupervised and domain adaptation RE-ID methods.

Blind Quality Assessment of Iris Images Acquired in Visible Light for Biometric Recognition.

Image quality is a key issue affecting the performance of biometric systems. Ensuring the quality of iris images acquired in unconstrained imaging conditions in visible light poses many challenges to iris recognition systems. Poor-quality iris images increase the false rejection rate and decrease the performance of the systems by quality filtering. Methods that can accurately predict iris image quality can improve the efficiency of quality-control protocols in iris recognition systems. We propose a fast blind/no-reference metric for predicting iris image quality. The proposed metric is based on statistical features of the sign and the magnitude of local image intensities. The experiments, conducted with a reference iris recognition system and three datasets of iris images acquired in visible light, showed that the quality of iris images strongly affects the recognition performance and is highly correlated with the iris matching scores. Rejecting poor-quality iris images improved the performance of the iris recognition system. In addition, we analyzed the effect of iris image quality on the accuracy of the iris segmentation module in the iris recognition system.

Genetic analysis identifies the missing parchment of New Zealand's founding document, the Treaty of Waitangi.

Genetic analyses provide a powerful tool with which to identify the biological components of historical objects. Te Tiriti o Waitangi | The Treaty of Waitangi is New Zealand's founding document, intended to be a partnership between the indigenous Maori and the British Crown. Here we focus on an archived piece of blank parchment that has been proposed to be the missing portion of the lower parchment of the Waitangi Sheet of the Treaty. However, its physical dimensions and characteristics are not consistent with this hypothesis. We perform genetic analyses on the parchment membranes of the Treaty, plus the blank piece of parchment. We find that all three parchments were made from ewes and that the blank parchment is highly likely to be a portion cut from the lower membrane of the Waitangi Sheet because they share identical whole mitochondrial genomes, including an unusual heteroplasmic site. We suggest that the differences in size and characteristics between the two pieces of parchment may have resulted from the Treaty's exposure to water in the early 20th century and the subsequent repair work, light exposure during exhibition or the later conservation treatments in the 1970s and 80s. The blank piece of parchment will be valuable for comparison tests to study the effects of earlier treatments and to monitor the effects of long-term display on the Treaty.

Forensic gait analysis - Morphometric assessment from surveillance footage.

Following the technological rise of surveillance cameras and their subsequent proliferation in public places, the use of information gathered by such means for investigative and evaluative purposes sparked a large interest in the forensic community and within policing scenarios. In particular, it is suggested that analysis of the body, especially the assessment of gait characteristics, can provide useful information to aid the investigation. This paper discusses the influences upon gait to mitigate some of the limitations of surveillance footage, including those due to the varying anatomical differences between individuals. Furthermore, the differences between various techniques applied to assess gait are discussed, including biometric gait recognition, forensic gait analysis, tracking technology, and marker technology. This review article discusses the limitations of the current methods for assessment of gait; exposing gaps within the literature in regard to various influences impacting upon the gait cycle. Furthermore, it suggests a 'morphometric' technique to enhance the available procedures to potentially facilitate the development of standardised protocols with supporting statistics and database. This in turn will provide meaningful information to forensic investigation, intelligence-gathering processes, and potentially as an additional method of forensic evaluation of evidence.

Impact of remote biometric monitoring on cost and hospitalization outcomes in peritoneal dialysis.

INTRODUCTION: Peritoneal dialysis is a home-based therapy for individuals with end-stage renal disease. Telehealth, and in particular - remote monitoring, is making inroads in managing this cohort. METHODS: We examined whether daily remote biometric monitoring (RBM) of blood pressure and weight among peritoneal dialysis patients was associated with changes in hospitalization rate and hospital length of stay, as well as outpatient, inpatient and overall cost of care. RESULTS: Outpatient visit claim payment amounts (in US dollars derived from CMS data) decreased post-intervention relative to pre-intervention for those at age 18-54 years. For certain subgroups, non- or nearly-significant changes were found among female and Black participants. There was no change in inpatient costs post-intervention relative to pre-intervention for females and while the overall visit claim payment amounts increased in the outpatient setting slightly (US$511.41 (1990.30) vs. US$652.61 (2319.02), p = 0.0783) and decreased in the inpatient setting (US$10,835.30 (6488.66) vs. US$10,678.88 (15,308.17), p = 0.4588), these differences were not statistically significant. Overall cost was lower if RBM was used for assessment of blood pressure and/or weight (US$-734.51, p < 0.05). Use of RBM collected weight was associated with fewer hospitalizations (adjusted odds ratio 0.54, 95% confidence interval 0.33-0.89) and fewer days hospitalized (adjusted odds ratio 0.46, 95% confidence interval 0.26-0.81). Use of RBM collected blood pressure was associated with increased days of hospitalization and increased odds of hospitalization. CONCLUSIONS: RBM offers a powerful opportunity to provide care to those receiving home therapies such as peritoneal dialysis. RBM may be associated with reduction in both inpatient and outpatient costs for specific sub-groups receiving peritoneal dialysis.

Perspectives of human verification via binary QRS template matching of single-lead and 12-lead electrocardiogram.

OBJECTIVE: This study aims to validate the 12-lead electrocardiogram (ECG) as a biometric modality based on two straightforward binary QRS template matching characteristics. Different perspectives of the human verification problem are considered, regarding the optimal lead selection and stability over sample size, gender, age, heart rate (HR). METHODS: A clinical 12-lead resting ECG database, including a population of 460 subjects with two-session recordings (>1 year apart) is used. Cost-effective strategies for extraction of personalized QRS patterns (100ms) and binary template matching estimate similarity in the time scale (matching time) and dissimilarity in the amplitude scale (mismatch area). The two-class person verification task, taking the decision to validate or to reject the subject identity is managed by linear discriminant analysis (LDA). Non-redundant LDA models for different lead configurations (I,II,III,aVF,aVL,aVF,V1-V6) are trained on the first half of 230 subjects by stepwise feature selection until maximization of the area under the receiver operating characteristic curve (ROC AUC). The operating point on the training ROC at equal error rate (EER) is tested on the independent dataset (second half of 230 subjects) to report unbiased validation of test-ROC AUC and true verification rate (TVR = 100-EER). The test results are further evaluated in groups by sample size, gender, age, HR. RESULTS AND DISCUSSION: The optimal QRS pattern projection for single-lead ECG biometric modality is found in the frontal plane sector (60°-0°) with best (Test-AUC/TVR) for lead II (0.941/86.8%) and slight accuracy drop for -aVR (-0.017/-1.4%), I (-0.01/-1.5%). Chest ECG leads have degrading accuracy from V1 (0.885/80.6%) to V6 (0.799/71.8%). The multi-lead ECG improves verification: 6-chest (0.97/90.9%), 6-limb (0.986/94.3%), 12-leads (0.995/97.5%). The QRS pattern matching model shows stable performance for verification of 10 to 230 individuals; insignificant degradation of TVR in women by (1.2-3.6%), adults ≥70 years (3.7%), younger <40 years (1.9%), HR<60bpm (1.2%), HR>90bpm (3.9%), no degradation for HR change (0 to >20bpm).

Cryptanalysis and improvement of a biometrics-based authentication and key agreement scheme for multi-server environments.

According to advancements in the wireless technologies, study of biometrics-based multi-server authenticated key agreement schemes has acquired a lot of momentum. Recently, Wang et al. presented a three-factor authentication protocol with key agreement and claimed that their scheme was resistant to several prominent attacks. Unfortunately, this paper indicates that their protocol is still vulnerable to the user impersonation attack, privileged insider attack and server spoofing attack. Furthermore, their protocol cannot provide the perfect forward secrecy. As a remedy of these aforementioned problems, we propose a biometrics-based authentication and key agreement scheme for multi-server environments. Compared with various related schemes, our protocol achieves the stronger security and provides more functionality properties. Besides, the proposed protocol shows the satisfactory performances in respect of storage requirement, communication overhead and computational cost. Thus, our protocol is suitable for expert systems and other multi-server architectures. Consequently, the proposed protocol is more appropriate in the distributed networks.

Face recognition algorithm using extended vector quantization histogram features.

In this paper, we propose a face recognition algorithm based on a combination of vector quantization (VQ) and Markov stationary features (MSF). The VQ algorithm has been shown to be an effective method for generating features; it extracts a codevector histogram as a facial feature representation for face recognition. Still, the VQ histogram features are unable to convey spatial structural information, which to some extent limits their usefulness in discrimination. To alleviate this limitation of VQ histograms, we utilize Markov stationary features (MSF) to extend the VQ histogram-based features so as to add spatial structural information. We demonstrate the effectiveness of our proposed algorithm by achieving recognition results superior to those of several state-of-the-art methods on publicly available face databases.

Active Self-Paced Learning for Cost-Effective and Progressive Face Identification.

This paper aims to develop a novel cost-effective framework for face identification, which progressively maintains a batch of classifiers with the increasing face images of different individuals. By naturally combining two recently rising techniques: active learning (AL) and self-paced learning (SPL), our framework is capable of automatically annotating new instances and incorporating them into training under weak expert recertification. We first initialize the classifier using a few annotated samples for each individual, and extract image features using the convolutional neural nets. Then, a number of candidates are selected from the unannotated samples for classifier updating, in which we apply the current classifiers ranking the samples by the prediction confidence. In particular, our approach utilizes the high-confidence and low-confidence samples in the self-paced and the active user-query way, respectively. The neural nets are later fine-tuned based on the updated classifiers. Such heuristic implementation is formulated as solving a concise active SPL optimization problem, which also advances the SPL development by supplementing a rational dynamic curriculum constraint. The new model finely accords with the "instructor-student-collaborative" learning mode in human education. The advantages of this proposed framework are two-folds: i) The required number of annotated samples is significantly decreased while the comparable performance is guaranteed. A dramatic reduction of user effort is also achieved over other state-of-the-art active learning techniques. ii) The mixture of SPL and AL effectively improves not only the classifier accuracy compared to existing AL/SPL methods but also the robustness against noisy data. We evaluate our framework on two challenging datasets, which include hundreds of persons under diverse conditions, and demonstrate very promising results. Please find the code of this project at: http://hcp.sysu.edu.cn/projects/aspl/.

Exploring the relationship between stride, stature and hand size for forensic assessment.

Forensic evidence often relies on a combination of accurately recorded measurements, estimated measurements from landmark data such as a subject's stature given a known measurement within an image, and inferred data. In this study a novel dataset is used to explore linkages between hand measurements, stature, leg length and stride. These three measurements replicate the type of evidence found in surveillance videos with stride being extracted from an automated gait analysis system. Through correlations and regression modelling, it is possible to generate accurate predictions of stature from hand size, leg length and stride length (and vice versa), and to predict leg and stride length from hand size with, or without, stature as an intermediary variable. The study also shows improved accuracy when a subject's sex is known a-priori. Our method and models indicate the possibility of calculating or checking relationships between a suspect's physical measurements, particularly when only one component is captured as an accurately recorded measurement.

Beat-ID: Towards a computationally low-cost single heartbeat biometric identity check system based on electrocardiogram wave morphology.

In recent years, safer and more reliable biometric methods have been developed. Apart from the need for enhanced security, the media and entertainment sectors have also been applying biometrics in the emerging market of user-adaptable objects/systems to make these systems more user-friendly. However, the complexity of some state-of-the-art biometric systems (e.g., iris recognition) or their high false rejection rate (e.g., fingerprint recognition) is neither compatible with the simple hardware architecture required by reduced-size devices nor the new trend of implementing smart objects within the dynamic market of the Internet of Things (IoT). It was recently shown that an individual can be recognized by extracting features from their electrocardiogram (ECG). However, most current ECG-based biometric algorithms are computationally demanding and/or rely on relatively large (several seconds) ECG samples, which are incompatible with the aforementioned application fields. Here, we present a computationally low-cost method (patent pending), including simple mathematical operations, for identifying a person using only three ECG morphology-based characteristics from a single heartbeat. The algorithm was trained/tested using ECG signals of different duration from the Physionet database on more than 60 different training/test datasets. The proposed method achieved maximal averaged accuracy of 97.450% in distinguishing each subject from a ten-subject set and false acceptance and rejection rates (FAR and FRR) of 5.710±1.900% and 3.440±1.980%, respectively, placing Beat-ID in a very competitive position in terms of the FRR/FAR among state-of-the-art methods. Furthermore, the proposed method can identify a person using an average of 1.020 heartbeats. It therefore has FRR/FAR behavior similar to obtaining a fingerprint, yet it is simpler and requires less expensive hardware. This method targets low-computational/energy-cost scenarios, such as tiny wearable devices (e.g., a smart object that automatically adapts its configuration to the user). A hardware proof-of-concept implementation is presented as an annex to this paper.

Ear biometrics for patient identification in global health: a cross-sectional study to test the feasibility of a simplified algorithm.

BACKGROUND: One of the greatest public health challenges in low- and middle-income countries (LMICs) is identifying people over time and space. Recent years have seen an explosion of interest in developing electronic approaches to addressing this problem, with mobile technology at the forefront of these efforts. We investigate the possibility of biometrics as a simple, cost-efficient, and portable solution. Common biometrics approaches include fingerprinting, iris scanning and facial recognition, but all are less than ideal due to complexity, infringement on privacy, cost, or portability. Ear biometrics, however, proved to be a unique and viable solution. METHODS: We developed an identification algorithm then conducted a cross sectional study in which we photographed left and right ears from 25 consenting adults. We then conducted re-identification and statistical analyses to identify the accuracy and replicability of our approach. RESULTS: Through principal component analysis, we found the curve of the ear helix to be the most reliable anatomical structure and the basis for re-identification. Although an individual ear allowed for high re-identification rate (88.3%), when both left and right ears were paired together, our rate of re-identification amidst the pool of potential matches was 100%. CONCLUSIONS: The results of this study have implications on future efforts towards building a biometrics solution for patient identification in LMICs. We provide a conceptual platform for further investigation into the development of an ear biometrics identification mobile application.

Validation of the facial assessment by computer evaluation (FACE) program for software-aided eyelid measurements.

The aim of this article is to validate the accuracy of Facial Assessment by Computer Evaluation (FACE) program in eyelid measurements. Sixteen subjects between the ages of 27 and 65 were included with IRB approval. Clinical measurements of upper eyelid margin reflex distance (MRD1) and inter-palpebral fissure (IPF) were obtained. Photographs were then taken with a digital single lens reflex camera with built-in pop-up flash (dSLR-pop) and a dSLR with lens-mounted ring flash (dSLR-ring) with the cameras upright, rotated 90, 180, and 270 degrees. The images were analyzed using both the FACE and ImageJ software to measure MRD1 and IPF.Thirty-two eyes of sixteen subjects were included. Comparison of clinical measurement of MRD1 and IPF with FACE measurements of photos in upright position showed no statistically significant differences for dSLR-pop (MRD1: p = 0.0912, IPF: p = 0.334) and for dSLR-ring (MRD1: p = 0.105, IPF: p = 0.538). One-to-one comparison of MRD1 and IPF measurements in four positions obtained with FACE versus ImageJ for dSLR-pop showed moderate to substantial agreement for MRD1 (intraclass correlation coefficient = 0.534 upright, 0.731 in 90 degree rotation, 0.627 in 180 degree rotation, 0.477 in 270 degree rotation) and substantial to excellent agreement in IPF (ICC = 0.740, 0.859, 0.849, 0.805). In photos taken with dSLR-ring, there was excellent agreement of all MRD1 (ICC = 0.916, 0.932, 0.845, 0.812) and IPF (ICC = 0.937, 0.938, 0.917, 0.888) values. The FACE program is a valid method for measuring margin reflex distance and inter-palpebral fissure.

Towards Contactless, Low-Cost and Accurate 3D Fingerprint Identification.

Human identification using fingerprint impressions has been widely studied and employed for more than 2000 years. Despite new advancements in the 3D imaging technologies, widely accepted representation of 3D fingerprint features and matching methodology is yet to emerge. This paper investigates 3D representation of widely employed 2D minutiae features by recovering and incorporating (i) minutiae height z and (ii) its 3D orientation φ information and illustrates an effective matching strategy for matching popular minutiae features extended in 3D space. One of the obstacles of the emerging 3D fingerprint identification systems to replace the conventional 2D fingerprint system lies in their bulk and high cost, which is mainly contributed from the usage of structured lighting system or multiple cameras. This paper attempts to addresses such key limitations of the current 3D fingerprint technologies bydeveloping the single camera-based 3D fingerprint identification system. We develop a generalized 3D minutiae matching model and recover extended 3D fingerprint features from the reconstructed 3D fingerprints. 2D fingerprint images acquired for the 3D fingerprint reconstruction can themselves be employed for the performance improvement and have been illustrated in the work detailed in this paper. This paper also attempts to answer one of the most fundamental questions on the availability of inherent discriminable information from 3D fingerprints. The experimental results are presented on a database of 240 clients 3D fingerprints, which is made publicly available to further research efforts in this area, and illustrate the discriminant power of 3D minutiae representation and matching to achieve performance improvement.

Markov Network-Based Unified Classifier for Face Recognition.

In this paper, we propose a novel unifying framework using a Markov network to learn the relationships among multiple classifiers. In face recognition, we assume that we have several complementary classifiers available, and assign observation nodes to the features of a query image and hidden nodes to those of gallery images. Under the Markov assumption, we connect each hidden node to its corresponding observation node and the hidden nodes of neighboring classifiers. For each observation-hidden node pair, we collect the set of gallery candidates most similar to the observation instance, and capture the relationship between the hidden nodes in terms of a similarity matrix among the retrieved gallery images. Posterior probabilities in the hidden nodes are computed using the belief propagation algorithm, and we use marginal probability as the new similarity value of the classifier. The novelty of our proposed framework lies in the method that considers classifier dependence using the results of each neighboring classifier. We present the extensive evaluation results for two different protocols, known and unknown image variation tests, using four publicly available databases: 1) the Face Recognition Grand Challenge ver. 2.0; 2) XM2VTS; 3) BANCA; and 4) Multi-PIE. The result shows that our framework consistently yields improved recognition rates in various situations.

Human facial expression recognition using stepwise linear discriminant analysis and hidden conditional random fields.

This paper introduces an accurate and robust facial expression recognition (FER) system. For feature extraction, the proposed FER system employs stepwise linear discriminant analysis (SWLDA). SWLDA focuses on selecting the localized features from the expression frames using the partial F-test values, thereby reducing the within class variance and increasing the low between variance among different expression classes. For recognition, the hidden conditional random fields (HCRFs) model is utilized. HCRF is capable of approximating a complex distribution using a mixture of Gaussian density functions. To achieve optimum results, the system employs a hierarchical recognition strategy. Under these settings, expressions are divided into three categories based on parts of the face that contribute most toward an expression. During recognition, at the first level, SWLDA and HCRF are employed to recognize the expression category; whereas, at the second level, the label for the expression within the recognized category is determined using a separate set of SWLDA and HCRF, trained just for that category. In order to validate the system, four publicly available data sets were used, and a total of four experiments were performed. The weighted average recognition rate for the proposed FER approach was 96.37% across the four different data sets, which is a significant improvement in contrast to the existing FER methods.

Control of origin of sesame oil from various countries by stable isotope analysis and DNA based markers--a pilot study.

The indication of origin of sesame seeds and sesame oil is one of the important factors influencing its price, as it is produced in many regions worldwide and certain provenances are especially sought after. We joined stable carbon and hydrogen isotope analysis with DNA based molecular marker analysis to study their combined potential for the discrimination of different origins of sesame seeds. For the stable carbon and hydrogen isotope data a positive correlation between both isotope parameters was observed, indicating a dominant combined influence of climate and water availability. This enabled discrimination between sesame samples from tropical and subtropical/moderate climatic provenances. Carbon isotope values also showed differences between oil from black and white sesame seeds from identical locations, indicating higher water use efficiency of plants producing black seeds. DNA based markers gave independent evidence for geographic variation as well as provided information on the genetic relatedness of the investigated samples. Depending on the differences in ambient environmental conditions and in the genotypic fingerprint, a combination of both analytical methods is a very powerful tool to assess the declared geographic origin. To our knowledge this is the first paper on food authenticity combining the stable isotope analysis of bio-elements with DNA based markers and their combined statistical analysis.

A Markov Random Field Groupwise Registration Framework for Face Recognition.

In this paper, we propose a new framework for tackling face recognition problem. The face recognition problem is formulated as groupwise deformable image registration and feature matching problem. The main contributions of the proposed method lie in the following aspects: (1) Each pixel in a facial image is represented by an anatomical signature obtained from its corresponding most salient scale local region determined by the survival exponential entropy (SEE) information theoretic measure. (2) Based on the anatomical signature calculated from each pixel, a novel Markov random field based groupwise registration framework is proposed to formulate the face recognition problem as a feature guided deformable image registration problem. The similarity between different facial images are measured on the nonlinear Riemannian manifold based on the deformable transformations. (3) The proposed method does not suffer from the generalizability problem which exists commonly in learning based algorithms. The proposed method has been extensively evaluated on four publicly available databases: FERET, CAS-PEAL-R1, FRGC ver 2.0, and the LFW. It is also compared with several state-of-the-art face recognition approaches, and experimental results demonstrate that the proposed method consistently achieves the highest recognition rates among all the methods under comparison.