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.

An investigation into the suitability of time-of-flight mass spectrometry in forensic toxicology

Liquid chromatography coupled with mass spectrometry is one of the most powerful tools in the toxicologist’s arsenal to detect a wide variety of compounds from many different matrices. However, the huge number of potentially abused substances and new substances especially designed as intoxicants poses a problem in a forensic toxicology setting. Most methods are targeted and designed to cover a very specific drug or group of drugs while many other substances remain undetected. High resolution mass spectrometry, more specifically time-of-flight mass spectrometry, represents an extremely powerful tool in analysing a multitude of compounds not only simultaneously but also retroactively. The data obtained through the time-of-flight instrument contains all compounds made available from sample extraction and chromatography, which can be processed at a later time with an improved library to detect previously unrecognised compounds without having to analyse the respective sample again. The aim of this project was to determine the utility and limitations of time-of-flight mass spectrometry as a general and easily expandable screening method. The resolution of time-of-flight mass spectrometry allows for the separation of compounds with the same nominal mass but distinct exact masses without the need to separate them chromatographically. To simulate the wide variety of potentially encountered drugs in such a general screening method, seven drugs (morphine, cocaine, zolpidem, diazepam, amphetamine, MDEA and THC) were chosen to represent this variety in terms of mass, properties and functional groups. Consequently, several liquid-liquid and solid phase extractions were applied to urine samples to determine the most general suitable and unspecific extraction. Chromatography was optimised by investigating the parameters pH, concentration, organic solvent and gradient of the mobile phase to improve data obtained by the time-of-flight instrument. The resulting method was validated as a qualitative confirmation/identification method. Data processing was automated using the software TargetAnalysis, which provides excellent analyte recognition according to retention time, exact mass and isotope pattern. The recognition of isotope patterns allows excellent recognition of analytes even in interference rich mass spectra and proved to be a good positive indicator. Finally, the validated method was applied to samples received from the A& E Department of Glasgow Royal Infirmary in suspected drug abuse cases and samples received from the Scottish Prison Service, which we received from their own prevalence study targeting drugs of abuse in the prison population. The obtained data was processed with a library established in the course of this work.