Improved facial expression recognition via uni-hyperplane classification

Large margin learning approaches, such as support vector machines (SVM), have been successfully applied to numerous classification tasks, especially for automatic facial expression recognition. The risk of such approaches however, is their sensitivity to large margin losses due to the influence from noisy training examples and outliers which is a common problem in the area of affective computing (i.e., manual coding at the frame level is tedious so coarse labels are normally assigned). In this paper, we leverage the relaxation of the parallel-hyperplanes constraint and propose the use of modified correlation filters (MCF). The MCF is similar in spirit to SVMs and correlation filters, but with the key difference of optimizing only a single hyperplane. We demonstrate the superiority of MCF over current techniques on a battery of experiments.

Mechanical considerations in fracture fixation

Bone’s capacity to repair following trauma is both unique and astounding. However, fractures sometimes fail to heal. Hence, the goal of fracture treatment is the restoration of bone’s structure, composition and function. Fracture fixation devices should provide a favourable mechanical and biological environment for healing to occur. The use of internal fixation is increasing as these devices may be applied with less invasive techniques. Recent studies suggest however that, internal fixation devices may be overly stiff and suppresses callus formation. The degree of mechanical stability influences the healing outcome. This is determined by the stiffness of the fixation device and the degree of limb loading. This project aims to characterise the fixation stability of an internal plate fixation device and the influence of modifications to its configuration on implant stability. As there are no standardised methods for the determination of fixation stiffness, the first part of this project aims to compares different methodologies and determines the most appropriate method to characterise the stiffness of internal plate fixators. The stiffness of a fixation device also influences the physiological loads experienced by the healing bone. Since bone adapts to this applied load by undergoing changes through a remodelling process, undesirable changes could occur during the period of treatment with an implant. The second part of this project aims to develop a methodology to quantify remodelling changes. This quantification is expected to aid our understanding of the changes in pattern due to implant related remodelling and on the factors driving the remodelling process. Knowledge gained in this project is useful to understand how the configuration of internal fixation devices can promote timely healing and prevent undesirable bone loss.

Influence of plate bending stiffness on mechanical properties of healing fracture, mouse femora

Mechanically well-defined stabilization systems have only recently become available, providing standardized conditions for studying the role of the mechanical environment on mouse bone fracture healing. The aim of this study was to characterize the time course of strength recovery and callus development of mouse femoral osteotomies stabilized with either low or high flexibility (in bending and torsion) internal fixation plates. Animals were euthanized and femora excised at 14, 21, and 28 days post-osteotomy for microCT analysis and torsional strength testing. While a larger mineralized callus was observed in osteotomies under more flexible conditions at all time points, the earlier bridging of the mineralized callus under less flexible conditions by 1 week resulted in an earlier recovery of torsional strength in mice stabilized with low flexibility fixation. Ultimate torque values for these bones were significantly higher at 14 and 21 days post-osteotomy compared to bones with the more flexible stabilization. Our study confirms the high reproducibility of the results that are achieved with this new implant system, therefore making it ideal for studying the influence of the mechanical environment on murine fracture healing under highly standardized conditions.

Tooth fracture risk analysis based on a new finite element dental structure models using micro-CT data

The finite element (FE) analysis is an effective method to study the strength and predict the fracture risk of endodontically-treated teeth. This paper presents a rapid method developed to generate a comprehensive tooth FE model using data retrieved from micro-computed tomography (μCT). With this method, the inhomogeneity of material properties of teeth was included into the model without dividing the tooth model into different regions. The material properties of the tooth were assumed to be related to the mineral density. The fracture risk at different tooth portions was assessed for root canal treatments. The micro-CT images of a tooth were processed by a Matlab software programme and the CT numbers were retrieved. The tooth contours were obtained with thresholding segmentation using Amira. The inner and outer surfaces of the tooth were imported into Solidworks and a three-dimensional (3D) tooth model was constructed. An assembly of the tooth model with the periodontal ligament (PDL) layer and surrounding bone was imported into ABAQUS. The material properties of the tooth were calculated from the retrieved CT numbers via ABAQUS user's subroutines. Three root canal geometries (original and two enlargements) were investigated. The proposed method in this study can generate detailed 3D finite element models of a tooth with different root canal enlargements and filling materials, and would be very useful for the assessment of the fracture risk at different tooth portions after root canal treatments.

Robust facial feature extraction and matching

Automated feature extraction and correspondence determination is an extremely important problem in the face recognition community as it often forms the foundation of the normalisation and database construction phases of many recognition and verification systems. This paper presents a completely automatic feature extraction system based upon a modified volume descriptor. These features form a stable descriptor for faces and are utilised in a reversible jump Markov chain Monte Carlo correspondence algorithm to automatically determine correspondences which exist between faces. The developed system is invariant to changes in pose and occlusion and results indicate that it is also robust to minor face deformations which may be present with variations in expression.

Towards spontaneous facial expression recognition in real-world video

Facial expression is an important channel of human social communication. Facial expression recognition (FER) aims to perceive and understand emotional states of humans based on information in the face. Building robust and high performance FER systems that can work in real-world video is still a challenging task, due to the various unpredictable facial variations and complicated exterior environmental conditions, as well as the difficulty of choosing a suitable type of feature descriptor for extracting discriminative facial information. Facial variations caused by factors such as pose, age, gender, race and occlusion, can exert profound influence on the robustness, while a suitable feature descriptor largely determines the performance. Most present attention on FER has been paid to addressing variations in pose and illumination. No approach has been reported on handling face localization errors and relatively few on overcoming facial occlusions, although the significant impact of these two variations on the performance has been proved and highlighted in many previous studies. Many texture and geometric features have been previously proposed for FER. However, few comparison studies have been conducted to explore the performance differences between different features and examine the performance improvement arisen from fusion of texture and geometry, especially on data with spontaneous emotions. The majority of existing approaches are evaluated on databases with posed or induced facial expressions collected in laboratory environments, whereas little attention has been paid on recognizing naturalistic facial expressions on real-world data. This thesis investigates techniques for building robust and high performance FER systems based on a number of established feature sets. It comprises of contributions towards three main objectives: (1) Robustness to face localization errors and facial occlusions. An approach is proposed to handle face localization errors and facial occlusions using Gabor based templates. Template extraction algorithms are designed to collect a pool of local template features and template matching is then performed to covert these templates into distances, which are robust to localization errors and occlusions. (2) Improvement of performance through feature comparison, selection and fusion. A comparative framework is presented to compare the performance between different features and different feature selection algorithms, and examine the performance improvement arising from fusion of texture and geometry. The framework is evaluated for both discrete and dimensional expression recognition on spontaneous data. (3) Evaluation of performance in the context of real-world applications. A system is selected and applied into discriminating posed versus spontaneous expressions and recognizing naturalistic facial expressions. A database is collected from real-world recordings and is used to explore feature differences between standard database images and real-world images, as well as between real-world images and real-world video frames. The performance evaluations are based on the JAFFE, CK, Feedtum, NVIE, Semaine and self-collected QUT databases. The results demonstrate high robustness of the proposed approach to the simulated localization errors and occlusions. Texture and geometry have different contributions to the performance of discrete and dimensional expression recognition, as well as posed versus spontaneous emotion discrimination. These investigations provide useful insights into enhancing robustness and achieving high performance of FER systems, and putting them into real-world applications.

Blood cultures for evaluation of early postoperative fever after femoral neck fracture surgery

PURPOSE. To evaluate the utility of blood cultures in the assessment of early postoperative fever in hip fracture patients with no other indicators of sepsis. METHODS. 101 blood cultures were drawn on postoperative days 0 to 5 to investigate 84 febrile episodes in 31 women and 30 men (mean age, 80 years) whose body temperature measured via the tympanic route was ≥38ºC. Culture results of these 61 patients were divided into culture-positive and culture-negative groups for comparison. RESULTS. Of the 101 blood cultures, only 2 were positive: one was obtained 5 days after dynamic hip screw fixation, and the other 4 days after hemiarthroplasty. Both blood cultures grew coagulase-negative staphylococcal species, which were deemed to be skin contaminants not requiring change of patient management. 44 of these patients were treated with oral or intravenous antibiotics for a period of time. CONCLUSION. The risk of bacteraemia in patients with postoperative fever but no other symptoms of infection is low. Routine procurement of blood cultures in such patients is ineffective and of limited utility.

Molecular dynamics simulation of fracture strength and morphology of defective graphene

Different types of defects can be introduced into graphene during material synthesis, and significantly influence the properties of graphene. In this work, we investigated the effects of structural defects, edge functionalisation and reconstruction on the fracture strength and morphology of graphene by molecular dynamics simulations. The minimum energy path analysis was conducted to investigate the formation of Stone-Wales defects. We also employed out-of-plane perturbation and energy minimization principle to study the possi-ble morphology of graphene nanoribbons with edge-termination. Our numerical results show that the fracture strength of graphene is dependent on defects and environmental temperature. However, pre-existing defects may be healed, resulting in strength recovery. Edge functionalization can induce compressive stress and ripples in the edge areas of gra-phene nanoribbons. On the other hand, edge reconstruction contributed to the tensile stress and curved shape in the graphene nanoribbons.

A case for optimising fracture healing through inverse dynamization

The mechanical conditions in the repair tissues are known to influence the outcome of fracture healing. These mechanical conditions are determined by the stiffness of fixation and limb loading. Experimental studies have shown that there is a range of beneficial fixation stiffness for timely healing and that fixation stiffness that is either too flexible or too stiff impairs callus healing. However, much less is known about how mechanical conditions influence the biological processes that make up the sequence of bone repair and if indeed mechanical stimulation is required at all stages of repair. Secondary bone healing occurs through a sequence of events broadly characterised by inflammation, proliferation, consolidation and remodelling. It is our hypothesis that a change in fixation stiffness from very flexible to stiff can shorten the time to healing relative to constant fixation stiffness. Flexible fixation has the benefit of promoting greater callus formation and needs to be applied during the proliferative stage of repair. The greater callus size helps to stabilize the fragments earlier allowing mineralization to occur faster. Together with stable/rigid fixation applied during the latter stage of repair to ensure mineralization of the callus. The predicted benefits of inverse dynamization are shortened healing in comparison to very flexible fixation and healing time comparable or faster than stable fixation with greater callus stiffness.

A new model to study healing of a complex femur fracture with concurrent soft tissue injury in sheep

High energy bone fractures resulting from impact trauma are often accompanied by subcutaneous soft tissue injuries, even if the skin remains intact. There is evidence that such closed soft tissue injuries affect the healing of bone fractures, and vice versa. Despite this knowledge, most impact trauma studies in animals have focussed on bone fractures or soft tissue trauma in isolation. However, given the simultaneous impact on both tissues a better understanding of the interaction between these two injuries is necessary to optimise clinical treatment. The aim of this study was therefore to develop a new experimental model and characterise, for the first time, the healing of a complex fracture with concurrent closed soft tissue trauma in sheep. A pendulum impact device was designed to deliver a defined and standardised impact to the distal thigh of sheep, causing a reproducible contusion injury to the subcutaneous soft tissues. In a subsequent procedure, a reproducible femoral butterfly fracture (AO C3-type) was created at the sheep’s femur, which was initially stabilised for 5 days by an external fixator construct to allow for soft tissue swelling to recede, and ultimately in a bridging construct using locking plates. The combined injuries were applied to twelve sheep and the healing observed for four or eight weeks (six animals per group) until sacrifice. The pendulum impact led to a moderate to severe circumferential soft tissue injury with significant bruising, haematomas and partial muscle disruptions. Posttraumatic measurements showed elevated intra-compartmental pressure and circulatory tissue breakdown markers, with recovery to normal, pre-injury values within four days. Clinically, no neurovascular deficiencies were observed. Bi-weekly radiological analysis of the healing fractures showed progressive callus healing over time, with the average number of callus bridges increasing from 0.4 at two weeks to 4.2 at eight weeks. Biomechanical testing after sacrifice showed increasing torsional stiffness between four and eight weeks healing time from 10% to 100%, and increasing ultimate torsional strength from 10% to 64% (relative to the contralateral control limb). Our results demonstrate the robust healing of a complex femur fracture in the presence of a severe soft tissue contusion injury in sheep and demonstrate the establishment of a clinically relevant experimental model, for research aimed at improving the treatment of bone fractures accompanied by closed soft tissue injuries.

Oropharyngeal dysphagia in an elderly post-operative hip fracture population : a prospective cohort study

Background: normal ageing processes impact on oropharyngeal swallowing function placing older adults at risk of developing oropharyngeal dysphagia (OD). Anecdotal clinical experience has observed that older patients recovering from hip fracture surgery commonly develop OD post-operatively. Objective: to document the presence of OD following hip fracture surgery, and the factors associated with OD. Methods: one hundred and eighty-one patients with a mean age of 83 years (range: 65–103) admitted to a specialised orthogeriatric unit were assessed for OD post-surgery for hip fracture. Pre-admission, intra-operative and post-operative factors were examined to determine their relationship with the presence of OD. Results: OD was found to be present post-operatively in 34% (n = 61) of the current population. Multivariate logistic regression analyses revealed the presence of pre-existing neurological and respiratory medical co-morbidities, presence of post-operative delirium, age and living in a residential aged care facility prior to hospital admission to be associated with the post-operative OD. Conclusion: these results highlight that OD is present in a large number of the older hip fracture population. Early identification of OD has important implications for the provision of timely dysphagia management that may prevent secondary complications and potentially reduce the hospital length of stay.