Super-Fine Attributes with Crowd Prototyping.

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.

Method to assess the temporal persistence of potential biometric features: Application to oculomotor, gait, face and brain structure databases.

We introduce the intraclass correlation coefficient (ICC) to the biometric community as an index of the temporal persistence, or stability, of a single biometric feature. It requires, as input, a feature on an interval or ratio scale, and which is reasonably normally distributed, and it can only be calculated if each subject is tested on 2 or more occasions. For a biometric system, with multiple features available for selection, the ICC can be used to measure the relative stability of each feature. We show, for 14 distinct data sets (1 synthetic, 8 eye-movement-related, 2 gait-related, and 2 face-recognition-related, and one brain-structure-related), that selecting the most stable features, based on the ICC, resulted in the best biometric performance generally. Analyses based on using only the most stable features produced superior Rank-1-Identification Rate (Rank-1-IR) performance in 12 of 14 databases (p = 0.0065, one-tailed), when compared to other sets of features, including the set of all features. For Equal Error Rate (EER), using a subset of only high-ICC features also produced superior performance in 12 of 14 databases (p = 0. 0065, one-tailed). In general, then, for our databases, prescreening potential biometric features, and choosing only highly reliable features yields better performance than choosing lower ICC features or than choosing all features combined. We also determined that, as the ICC of a group of features increases, the median of the genuine similarity score distribution increases and the spread of this distribution decreases. There was no statistically significant similar relationships for the impostor distributions. We believe that the ICC will find many uses in biometric research. In case of the eye movement-driven biometrics, the use of reliable features, as measured by ICC, allowed to us achieve the authentication performance with EER = 2.01%, which was not possible before.

Soft Biometrics; Human Identification Using Comparative Descriptions.

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.

Self-calibrating view-invariant gait biometrics.

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

Developing geostatistical space-time models to predict outpatient treatment burdens from incomplete national data.

Basic health system data such as the number of patients utilising different health facilities and the types of illness for which they are being treated are critical for managing service provision. These data requirements are generally addressed with some form of national Health Management Information System (HMIS) which coordinates the routine collection and compilation of data from national health facilities. HMIS in most developing countries are characterised by widespread under-reporting. Here we present a method to adjust incomplete data to allow prediction of national outpatient treatment burdens. We demonstrate this method with the example of outpatient treatments for malaria within the Kenyan HMIS. Three alternative modelling frameworks were developed and tested in which space-time geostatistical prediction algorithms were used to predict the monthly tally of treatments for presumed malaria cases (MC) at facilities where such records were missing. Models were compared by a cross-validation exercise and the model found to most accurately predict MC incorporated available data on the total number of patients visiting each facility each month. A space-time stochastic simulation framework to accompany this model was developed and tested in order to provide estimates of both local and regional prediction uncertainty. The level of accuracy provided by the predictive model, and the accompanying estimates of uncertainty around the predictions, demonstrate how this tool can mitigate the uncertainties caused by missing data, substantially enhancing the utility of existing HMIS data to health-service decision-makers.

Improving imperfect data from health management information systems in Africa using space-time geostatistics.

BACKGROUND: Reliable and timely information on disease-specific treatment burdens within a health system is critical for the planning and monitoring of service provision. Health management information systems (HMIS) exist to address this need at national scales across Africa but are failing to deliver adequate data because of widespread underreporting by health facilities. Faced with this inadequacy, vital public health decisions often rely on crudely adjusted regional and national estimates of treatment burdens. METHODS AND FINDINGS: This study has taken the example of presumed malaria in outpatients within the largely incomplete Kenyan HMIS database and has defined a geostatistical modelling framework that can predict values for all data that are missing through space and time. The resulting complete set can then be used to define treatment burdens for presumed malaria at any level of spatial and temporal aggregation. Validation of the model has shown that these burdens are quantified to an acceptable level of accuracy at the district, provincial, and national scale. CONCLUSIONS: The modelling framework presented here provides, to our knowledge for the first time, reliable information from imperfect HMIS data to support evidence-based decision-making at national and sub-national levels.

Empirical modelling of government health service use by children with fevers in Kenya.

An understanding of spatial patterns of health facility use allows a more informed approach to the modelling of catchment populations. In the absence of patient use data, an intuitive and commonly used approach to the delineation of facility catchment areas is Thiessen polygons. This study presents a series of methods by which the validity of these assumptions can be tested directly and hence the suitability of a Thiessen polygon catchment model explicitly assessed. These methods are applied to paediatric out-patient origin data from a sample of 81 government health facilities in four districts of Kenya. A geographical information system was used to predict the location of the catchment boundary along a transect between each pair of neighbouring facilities based on patient choice patterns. The mean location of boundaries between facilities of different type was found to be significantly displaced from the Thiessen boundary towards the lower-order facility. The affect of distance on within-catchment utilization rate was assessed by using exclusion buffers to remove the effect of neighbouring facilities. Utilization rate was found to exhibit a slight but steady decrease with distance up to 6 km from a facility. The accuracy of the future modelling of unsampled facility catchments can be increased by the incorporation of these trends.

Automated segmentation of lumbar vertebrae in digital videofluoroscopic images.

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.