On robust face recognition via sparse coding: The good, the bad and the ugly

In the field of face recognition, sparse representation (SR) has received considerable attention during the past few years, with a focus on holistic descriptors in closed-set identification applications. The underlying assumption in such SR-based methods is that each class in the gallery has sufficient samples and the query lies on the subspace spanned by the gallery of the same class. Unfortunately, such an assumption is easily violated in the face verification scenario, where the task is to determine if two faces (where one or both have not been seen before) belong to the same person. In this study, the authors propose an alternative approach to SR-based face verification, where SR encoding is performed on local image patches rather than the entire face. The obtained sparse signals are pooled via averaging to form multiple region descriptors, which then form an overall face descriptor. Owing to the deliberate loss of spatial relations within each region (caused by averaging), the resulting descriptor is robust to misalignment and various image deformations. Within the proposed framework, they evaluate several SR encoding techniques: l1-minimisation, Sparse Autoencoder Neural Network (SANN) and an implicit probabilistic technique based on Gaussian mixture models. Thorough experiments on AR, FERET, exYaleB, BANCA and ChokePoint datasets show that the local SR approach obtains considerably better and more robust performance than several previous state-of-the-art holistic SR methods, on both the traditional closed-set identification task and the more applicable face verification task. The experiments also show that l1-minimisation-based encoding has a considerably higher computational cost when compared with SANN-based and probabilistic encoding, but leads to higher recognition rates.

Robust iris recognition using decision fusion and degradation modelling

This thesis investigates the use of fusion techniques and mathematical modelling to increase the robustness of iris recognition systems against iris image quality degradation, pupil size changes and partial occlusion. The proposed techniques improve recognition accuracy and enhance security. They can be further developed for better iris recognition in less constrained environments that do not require user cooperation. A framework to analyse the consistency of different regions of the iris is also developed. This can be applied to improve recognition systems using partial iris images, and cancelable biometric signatures or biometric based cryptography for privacy protection.

Conceptualising recognition of prior learning processes in the age of open learning

This chapter interrogates what recognition of prior learning (RPL) can and does mean in the higher education sector—a sector in the grip of the widening participation agenda and an open access age. The chapter discusses how open learning is making inroads into recognition processes and examines two studies in open learning recognition. A case study relating to e-portfolio-style RPL for entry into a Graduate Certificate in Policy and Governance at a metropolitan university in Queensland is described. In the first instance, candidates who do not possess a relevant Bachelor degree need to demonstrate skills in governmental policy work in order to be eligible to gain entry to a Graduate Certificate (at Australian Qualifications Framework Level 8) (Australian Qualifications Framework Council, 2013, p. 53). The chapter acknowledges the benefits and limitations of recognition in open learning and those of more traditional RPL, anticipating future developments in both (or their convergence).

Repeatable Condition-Invariant Visual Odometry for Sequence-Based Place Recognition

This paper describes a vision-only system for place recognition in environments that are tra- versed at different times of day, when chang- ing conditions drastically affect visual appear- ance, and at different speeds, where places aren’t visited at a consistent linear rate. The ma- jor contribution is the removal of wheel-based odometry from the previously presented algo- rithm (SMART), allowing the technique to op- erate on any camera-based device; in our case a mobile phone. While we show that the di- rect application of visual odometry to our night- time datasets does not achieve a level of perfor- mance typically needed, the VO requirements of SMART are orthogonal to typical usage: firstly only the magnitude of the velocity is required, and secondly the calculated velocity signal only needs to be repeatable in any one part of the environment over day and night cycles, but not necessarily globally consistent. Our results show that the smoothing effect of motion constraints is highly beneficial for achieving a locally consis- tent, lighting-independent velocity estimate. We also show that the advantage of our patch-based technique used previously for frame recogni- tion, surprisingly, does not transfer to VO, where SIFT demonstrates equally good performance. Nevertheless, we present the SMART system us- ing only vision, which performs sequence-base place recognition in extreme low-light condi- tions where standard 6-DOF VO fails and that improves place recognition performance over odometry-less benchmarks, approaching that of wheel odometry.

Understanding the determinants of Australian hospital nurses' hand hygiene decisions following the implementation of a national hand hygiene initiative

Hand hygiene is the primary measure in hospitals to reduce the spread of infections, with nurses experiencing the greatest frequency of patient contact. The ‘5 critical moments’ of hand hygiene initiative has been implemented in hospitals across Australia, accompanied by awareness-raising, staff training and auditing. The aim of this study was to understand the determinants of nurses’ hand hygiene decisions, using an extension of a common health decision-making model, the theory of planned behaviour (TPB), to inform future health education strategies to increase compliance. Nurses from 50 Australian hospitals (n = 2378) completed standard TPB measures (attitude, subjective norm, perceived behavioural control [PBC], intention) and the extended variables of group norm, risk perceptions (susceptibility, severity) and knowledge (subjective, objective) at Time 1, while a sub-sample (n = 797) reported their hand hygiene behaviour 2 weeks later. Regression analyses identified subjective norm, PBC, group norm, subjective knowledge and risk susceptibility as the significant predictors of nurses’ hand hygiene intentions, with intention and PBC predicting their compliance behaviour. Rather than targeting attitudes which are already very favourable among nurses, health education strategies should focus on normative influences and perceptions of control and risk in efforts to encourage hand hygiene adherence.

Enhancing human action recognition with region proposals

Deep convolutional network models have dominated recent work in human action recognition as well as image classification. However, these methods are often unduly influenced by the image background, learning and exploiting the presence of cues in typical computer vision datasets. For unbiased robotics applications, the degree of variation and novelty in action backgrounds is far greater than in computer vision datasets. To address this challenge, we propose an “action region proposal” method that, informed by optical flow, extracts image regions likely to contain actions for input into the network both during training and testing. In a range of experiments, we demonstrate that manually segmenting the background is not enough; but through active action region proposals during training and testing, state-of-the-art or better performance can be achieved on individual spatial and temporal video components. Finally, we show by focusing attention through action region proposals, we can further improve upon the existing state-of-the-art in spatio-temporally fused action recognition performance.

Recognition and enforcement in cross-border insolvency law: A proposal for judicial gap-filling

This Article analyzes the recognition and enforcement of cross-border insolvency judgments from the United States, United Kingdom, and Australia to determine whether the UNCITRAL Model Law’s goal of modified universalism is currently being practiced, and subjects the Model Law to analysis through the lens of international relations theories to elaborate a way forward. We posit that courts could use the express language of the Model Law text to confer recognition and enforcement of foreign insolvency judgments. The adoption of our proposal will reduce costs, maximize recovery for creditors, and ensure predictability for all parties.

Activity recognition using binary tree SVM

This paper presents an effective classification method based on Support Vector Machines (SVM) in the context of activity recognition. Local features that capture both spatial and temporal information in activity videos have made significant progress recently. Efficient and effective features, feature representation and classification plays a crucial role in activity recognition. For classification, SVMs are popularly used because of their simplicity and efficiency; however the common multi-class SVM approaches applied suffer from limitations including having easily confused classes and been computationally inefficient. We propose using a binary tree SVM to address the shortcomings of multi-class SVMs in activity recognition. We proposed constructing a binary tree using Gaussian Mixture Models (GMM), where activities are repeatedly allocated to subnodes until every new created node contains only one activity. Then, for each internal node a separate SVM is learned to classify activities, which significantly reduces the training time and increases the speed of testing compared to popular the `one-against-the-rest' multi-class SVM classifier. Experiments carried out on the challenging and complex Hollywood dataset demonstrates comparable performance over the baseline bag-of-features method.

Cost-effectiveness of a national initiative to improve hand hygiene compliance using the outcome of healthcare associated staphylococcus aureus bacteraemia

Background The objective is to estimate the incremental cost-effectiveness of the Australian National Hand Hygiene Inititiave implemented between 2009 and 2012 using healthcare associated Staphylococcus aureus bacteraemia as the outcome. Baseline comparators are the eight existing state and territory hand hygiene programmes. The setting is the Australian public healthcare system and 1,294,656 admissions from the 50 largest Australian hospitals are included. Methods The design is a cost-effectiveness modelling study using a before and after quasi-experimental design. The primary outcome is cost per life year saved from reduced cases of healthcare associated Staphylococcus aureus bacteraemia, with cost estimated by the annual on-going maintenance costs less the costs saved from fewer infections. Data were harvested from existing sources or were collected prospectively and the time horizon for the model was 12 months, 2011–2012. Findings No useable pre-implementation Staphylococcus aureus bacteraemia data were made available from the 11 study hospitals in Victoria or the single hospital in Northern Territory leaving 38 hospitals among six states and territories available for cost-effectiveness analyses. Total annual costs increased by $2,851,475 for a return of 96 years of life giving an incremental cost-effectiveness ratio (ICER) of $29,700 per life year gained. Probabilistic sensitivity analysis revealed a 100% chance the initiative was cost effective in the Australian Capital Territory and Queensland, with ICERs of $1,030 and $8,988 respectively. There was an 81% chance it was cost effective in New South Wales with an ICER of $33,353, a 26% chance for South Australia with an ICER of $64,729 and a 1% chance for Tasmania and Western Australia. The 12 hospitals in Victoria and the Northern Territory incur annual on-going maintenance costs of $1.51M; no information was available to describe cost savings or health benefits. Conclusions The Australian National Hand Hygiene Initiative was cost-effective against an Australian threshold of $42,000 per life year gained. The return on investment varied among the states and territories of Australia.

Diabetic charcot neuroarthropathy of the hand: Clinical course, diagnosis, and treatment options

During the treatment of diabetic Charcot neuroarthropathy (CN) of the foot in two young patients, we discovered atypical alterations of their hands with loss of strength and paresthesia combined with atypical and nonhealing bone alterations and instability. Whereas CN of the foot is a serious and well-known complication of diabetes, CN of the hand is only mentioned in four articles (1–4).

Human action recognition from video sequences

This PhD research has proposed new machine learning techniques to improve human action recognition based on local features. Several novel video representation and classification techniques have been proposed to increase the performance with lower computational complexity. The major contributions are the construction of new feature representation techniques, based on advanced machine learning techniques such as multiple instance dictionary learning, Latent Dirichlet Allocation (LDA) and Sparse coding. A Binary-tree based classification technique was also proposed to deal with large amounts of action categories. These techniques are not only improving the classification accuracy with constrained computational resources but are also robust to challenging environmental conditions. These developed techniques can be easily extended to a wide range of video applications to provide near real-time performance.

Elliptical summary randomisation for sensor-based human activity recognition

Many conventional statistical machine learning al- gorithms generalise poorly if distribution bias ex- ists in the datasets. For example, distribution bias arises in the context of domain generalisation, where knowledge acquired from multiple source domains need to be used in a previously unseen target domains. We propose Elliptical Summary Randomisation (ESRand), an efficient domain generalisation approach that comprises of a randomised kernel and elliptical data summarisation. ESRand learns a domain interdependent projection to a la- tent subspace that minimises the existing biases to the data while maintaining the functional relationship between domains. In the latent subspace, ellipsoidal summaries replace the samples to enhance the generalisation by further removing bias and noise in the data. Moreover, the summarisation enables large-scale data processing by significantly reducing the size of the data. Through comprehensive analysis, we show that our subspace-based approach outperforms state-of-the-art results on several activity recognition benchmark datasets, while keeping the computational complexity significantly low.