Hierarchically grouped 2D local features applied to edge contour localisation

One of the most significant research topics in computer vision is object detection. Most of the reported object detection results localise the detected object within a bounding box, but do not explicitly label the edge contours of the object. Since object contours provide a fundamental diagnostic of object shape, some researchers have initiated work on linear contour feature representations for object detection and localisation. However, linear contour feature-based localisation is highly dependent on the performance of linear contour detection within natural images, and this can be perturbed significantly by a cluttered background. In addition, the conventional approach to achieving rotation-invariant features is to rotate the feature receptive field to align with the local dominant orientation before computing the feature representation. Grid resampling after rotation adds extra computational cost and increases the total time consumption for computing the feature descriptor. Though it is not an expensive process if using current computers, it is appreciated that if each step of the implementation is faster to compute especially when the number of local features is increasing and the application is implemented on resource limited ”smart devices”, such as mobile phones, in real-time. Motivated by the above issues, a 2D object localisation system is proposed in this thesis that matches features of edge contour points, which is an alternative method that takes advantage of the shape information for object localisation. This is inspired by edge contour points comprising the basic components of shape contours. In addition, edge point detection is usually simpler to achieve than linear edge contour detection. Therefore, the proposed localization system could avoid the need for linear contour detection and reduce the pathological disruption from the image background. Moreover, since natural images usually comprise many more edge contour points than interest points (i.e. corner points), we also propose new methods to generate rotation-invariant local feature descriptors without pre-rotating the feature receptive field to improve the computational efficiency of the whole system. In detail, the 2D object localisation system is achieved by matching edge contour points features in a constrained search area based on the initial pose-estimate produced by a prior object detection process. The local feature descriptor obtains rotation invariance by making use of rotational symmetry of the hexagonal structure. Therefore, a set of local feature descriptors is proposed based on the hierarchically hexagonal grouping structure. Ultimately, the 2D object localisation system achieves a very promising performance based on matching the proposed features of edge contour points with the mean correct labelling rate of the edge contour points 0.8654 and the mean false labelling rate 0.0314 applied on the data from Amsterdam Library of Object Images (ALOI). Furthermore, the proposed descriptors are evaluated by comparing to the state-of-the-art descriptors and achieve competitive performances in terms of pose estimate with around half-pixel pose error.

Administrative justice and the control of bureaucratic decision-making: A study investigating how decision-makers in local authority education departments respond to the work of redress mechanisms

This socio-legal thesis has explored the factors responsible for explaining whether and how redress mechanisms control bureaucratic decision-making. The research considered the three principal institutions of administrative justice: courts, tribunals, and ombudsman schemes. The field setting was the local authority education area and the thesis examined bureaucratic decision-making about admissions to school, home-to-school transport, and Special Educational Needs (SEN). The thesis adopted a qualitative approach, using interviews and documentary research, within a multiple embedded case study design. The intellectual foundations of the research were inter-disciplinary, cutting across law, socio-legal studies, public administration, organization studies, and social policy. The thesis drew on these scholarly fields to explore the nature of bureaucratic decision-making, the extent to which it can be controlled and the way that learning occurs in bureaucracies and, finally, the extent to which redress mechanisms might exercise control. The concept of control was studied across all its dimensions – in relation both to ex post control in specific cases and the more challenging notion of ex ante or structuring control. The aim of the thesis was not to measure the prevalence of bureaucratic control by redress mechanisms, but to understand the factors that might explain its presence or absence in a particular area. The findings of the research have allowed for a number of analytical refinements and extensions to be made to existing theoretical and empirical understandings. 14 factors, along with 87 supporting propositions, have been set out with the aim of making empirically derived suggestions which can be followed up in future research. In terms of the thesis’ contribution to existing knowledge, its comparative focus and its emphasis on the broad notion of control offered the potential for new insights to be developed. Overall, the thesis claims to have made three contributions to the conceptual framework for understanding the exercise of control by redress mechanisms: it emphasizes the importance of ‘feedback’ in relation to the nature of the cases referred to redress mechanisms; it calls attention to the structure of bureaucratic decision-making as well as its normative character; and it discusses how the operational modes of redress mechanisms relate to their control functions.