Spectral coding methods for speech compression and speaker identification

This thesis investigates aspects of encoding the speech spectrum at low bit rates, with extensions to the effect of such coding on automatic speaker identification. Vector quantization (VQ) is a technique for jointly quantizing a block of samples at once, in order to reduce the bit rate of a coding system. The major drawback in using VQ is the complexity of the encoder. Recent research has indicated the potential applicability of the VQ method to speech when product code vector quantization (PCVQ) techniques are utilized. The focus of this research is the efficient representation, calculation and utilization of the speech model as stored in the PCVQ codebook. In this thesis, several VQ approaches are evaluated, and the efficacy of two training algorithms is compared experimentally. It is then shown that these productcode vector quantization algorithms may be augmented with lossless compression algorithms, thus yielding an improved overall compression rate. An approach using a statistical model for the vector codebook indices for subsequent lossless compression is introduced. This coupling of lossy compression and lossless compression enables further compression gain. It is demonstrated that this approach is able to reduce the bit rate requirement from the current 24 bits per 20 millisecond frame to below 20, using a standard spectral distortion metric for comparison. Several fast-search VQ methods for use in speech spectrum coding have been evaluated. The usefulness of fast-search algorithms is highly dependent upon the source characteristics and, although previous research has been undertaken for coding of images using VQ codebooks trained with the source samples directly, the product-code structured codebooks for speech spectrum quantization place new constraints on the search methodology. The second major focus of the research is an investigation of the effect of lowrate spectral compression methods on the task of automatic speaker identification. The motivation for this aspect of the research arose from a need to simultaneously preserve the speech quality and intelligibility and to provide for machine-based automatic speaker recognition using the compressed speech. This is important because there are several emerging applications of speaker identification where compressed speech is involved. Examples include mobile communications where the speech has been highly compressed, or where a database of speech material has been assembled and stored in compressed form. Although these two application areas have the same objective - that of maximizing the identification rate - the starting points are quite different. On the one hand, the speech material used for training the identification algorithm may or may not be available in compressed form. On the other hand, the new test material on which identification is to be based may only be available in compressed form. Using the spectral parameters which have been stored in compressed form, two main classes of speaker identification algorithm are examined. Some studies have been conducted in the past on bandwidth-limited speaker identification, but the use of short-term spectral compression deserves separate investigation. Combining the major aspects of the research, some important design guidelines for the construction of an identification model when based on the use of compressed speech are put forward.

A prototype system for the digital lodgement of spatial data

This dissertation develops the model of a prototype system for the digital lodgement of spatial data sets with statutory bodies responsible for the registration and approval of land related actions under the Torrens Title system. Spatial data pertain to the location of geographical entities together with their spatial dimensions and are classified as point, line, area or surface. This dissertation deals with a sub-set of spatial data, land boundary data that result from the activities performed by surveying and mapping organisations for the development of land parcels. The prototype system has been developed, utilising an event-driven paradigm for the user-interface, to exploit the potential of digital spatial data being generated from the utilisation of electronic techniques. The system provides for the creation of a digital model of the cadastral network and dependent data sets for an area of interest from hard copy records. This initial model is calibrated on registered control and updated by field survey to produce an amended model. The field-calibrated model then is electronically validated to ensure it complies with standards of format and content. The prototype system was designed specifically to create a database of land boundary data for subsequent retrieval by land professionals for surveying, mapping and related activities. Data extracted from this database are utilised for subsequent field survey operations without the need to create an initial digital model of an area of interest. Statistical reporting of differences resulting when subsequent initial and calibrated models are compared, replaces the traditional checking operations of spatial data performed by a land registry office. Digital lodgement of survey data is fundamental to the creation of the database of accurate land boundary data. This creation of the database is fundamental also to the efficient integration of accurate spatial data about land being generated by modem technology such as global positioning systems, and remote sensing and imaging, with land boundary information and other information held in Government databases. The prototype system developed provides for the delivery of accurate, digital land boundary data for the land registration process to ensure the continued maintenance of the integrity of the cadastre. Such data should meet also the more general and encompassing requirements of, and prove to be of tangible, longer term benefit to the developing, electronic land information industry.

Reliability analysis of transform-based stereo matching techniques, and a new matching constraint

Stereo vision is a method of depth perception, in which depth information is inferred from two (or more) images of a scene, taken from different perspectives. Practical applications for stereo vision include aerial photogrammetry, autonomous vehicle guidance, robotics and industrial automation. The initial motivation behind this work was to produce a stereo vision sensor for mining automation applications. For such applications, the input stereo images would consist of close range scenes of rocks. A fundamental problem faced by matching algorithms is the matching or correspondence problem. This problem involves locating corresponding points or features in two images. For this application, speed, reliability, and the ability to produce a dense depth map are of foremost importance. This work implemented a number of areabased matching algorithms to assess their suitability for this application. Area-based techniques were investigated because of their potential to yield dense depth maps, their amenability to fast hardware implementation, and their suitability to textured scenes such as rocks. In addition, two non-parametric transforms, the rank and census, were also compared. Both the rank and the census transforms were found to result in improved reliability of matching in the presence of radiometric distortion - significant since radiometric distortion is a problem which commonly arises in practice. In addition, they have low computational complexity, making them amenable to fast hardware implementation. Therefore, it was decided that matching algorithms using these transforms would be the subject of the remainder of the thesis. An analytic expression for the process of matching using the rank transform was derived from first principles. This work resulted in a number of important contributions. Firstly, the derivation process resulted in one constraint which must be satisfied for a correct match. This was termed the rank constraint. The theoretical derivation of this constraint is in contrast to the existing matching constraints which have little theoretical basis. Experimental work with actual and contrived stereo pairs has shown that the new constraint is capable of resolving ambiguous matches, thereby improving match reliability. Secondly, a novel matching algorithm incorporating the rank constraint has been proposed. This algorithm was tested using a number of stereo pairs. In all cases, the modified algorithm consistently resulted in an increased proportion of correct matches. Finally, the rank constraint was used to devise a new method for identifying regions of an image where the rank transform, and hence matching, are more susceptible to noise. The rank constraint was also incorporated into a new hybrid matching algorithm, where it was combined a number of other ideas. These included the use of an image pyramid for match prediction, and a method of edge localisation to improve match accuracy in the vicinity of edges. Experimental results obtained from the new algorithm showed that the algorithm is able to remove a large proportion of invalid matches, and improve match accuracy.

Basin analysis and economic geology of the Northern Mount Isa Basin

The Mount Isa Basin is a new concept used to describe the area of Palaeo- to Mesoproterozoic rocks south of the Murphy Inlier and inappropriately described presently as the Mount Isa Inlier. The new basin concept presented in this thesis allows for the characterisation of basin-wide structural deformation, correlation of mineralisation with particular lithostratigraphic and seismic stratigraphic packages, and the recognition of areas with petroleum exploration potential. The northern depositional margin of the Mount Isa Basin is the metamorphic, intrusive and volcanic complex here referred to as the Murphy Inlier (not the "Murphy Tectonic Ridge"). The eastern, southern and western boundaries of the basin are obscured by younger basins (Carpentaria, Eromanga and Georgina Basins). The Murphy Inlier rocks comprise the seismic basement to the Mount Isa Basin sequence. Evidence for the continuity of the Mount Isa Basin with the McArthur Basin to the northwest and the Willyama Block (Basin) at Broken Hill to the south is presented. These areas combined with several other areas of similar age are believed to have comprised the Carpentarian Superbasin (new term). The application of seismic exploration within Authority to Prospect (ATP) 423P at the northern margin of the basin was critical to the recognition and definition of the Mount Isa Basin. The Mount Isa Basin is structurally analogous to the Palaeozoic Arkoma Basin of Illinois and Arkansas in southern USA but, as with all basins it contains unique characteristics, a function of its individual development history. The Mount Isa Basin evolved in a manner similar to many well described, Phanerozoic plate tectonic driven basins. A full Wilson Cycle is recognised and a plate tectonic model proposed. The northern Mount Isa Basin is defined as the Proterozoic basin area northwest of the Mount Gordon Fault. Deposition in the northern Mount Isa Basin began with a rift sequence of volcaniclastic sediments followed by a passive margin drift phase comprising mostly carbonate rocks. Following the rift and drift phases, major north-south compression produced east-west thrusting in the south of the basin inverting the older sequences. This compression produced an asymmetric epi- or intra-cratonic clastic dominated peripheral foreland basin provenanced in the south and thinning markedly to a stable platform area (the Murphy Inlier) in the north. The fmal major deformation comprised east-west compression producing north-south aligned faults that are particularly prominent at Mount Isa. Potential field studies of the northern Mount Isa Basin, principally using magnetic data (and to a lesser extent gravity data, satellite images and aerial photographs) exhibit remarkable correlation with the reflection seismic data. The potential field data contributed significantly to the unravelling of the northern Mount Isa Basin architecture and deformation. Structurally, the Mount Isa Basin consists of three distinct regions. From the north to the south they are the Bowthorn Block, the Riversleigh Fold Zone and the Cloncurry Orogen (new names). The Bowthom Block, which is located between the Elizabeth Creek Thrust Zone and the Murphy Inlier, consists of an asymmetric wedge of volcanic, carbonate and clastic rocks. It ranges from over 10 000 m stratigraphic thickness in the south to less than 2000 min the north. The Bowthorn Block is relatively undeformed: however, it contains a series of reverse faults trending east-west that are interpreted from seismic data to be down-to-the-north normal faults that have been reactivated as thrusts. The Riversleigh Fold Zone is a folded and faulted region south of the Bowthorn Block, comprising much of the area formerly referred to as the Lawn Hill Platform. The Cloncurry Orogen consists of the area and sequences equivalent to the former Mount Isa Orogen. The name Cloncurry Orogen clearly distinguishes this area from the wider concept of the Mount Isa Basin. The South Nicholson Group and its probable correlatives, the Pilpah Sandstone and Quamby Conglomerate, comprise a later phase of now largely eroded deposits within the Mount Isa Basin. The name South Nicholson Basin is now outmoded as this terminology only applied to the South Nicholson Group unlike the original broader definition in Brown et al. (1968). Cored slimhole stratigraphic and mineral wells drilled by Amoco, Esso, Elf Aquitaine and Carpentaria Exploration prior to 1986, penetrated much of the stratigraphy and intersected both minor oil and gas shows plus excellent potential source rocks. The raw data were reinterpreted and augmented with seismic stratigraphy and source rock data from resampled mineral and petroleum stratigraphic exploration wells for this study. Since 1986, Comalco Aluminium Limited, as operator of a joint venture with Monument Resources Australia Limited and Bridge Oil Limited, recorded approximately 1000 km of reflection seismic data within the basin and drilled one conventional stratigraphic petroleum well, Beamesbrook-1. This work was the first reflection seismic and first conventional petroleum test of the northern Mount Isa Basin. When incorporated into the newly developed foreland basin and maturity models, a grass roots petroleum exploration play was recognised and this led to the present thesis. The Mount Isa Basin was seen to contain excellent source rocks coupled with potential reservoirs and all of the other essential aspects of a conventional petroleum exploration play. This play, although high risk, was commensurate with the enormous and totally untested petroleum potential of the basin. The basin was assessed for hydrocarbons in 1992 with three conventional exploration wells, Desert Creek-1, Argyle Creek-1 and Egilabria-1. These wells also tested and confrrmed the proposed basin model. No commercially viable oil or gas was encountered although evidence of its former existence was found. In addition to the petroleum exploration, indeed as a consequence of it, the association of the extensive base metal and other mineralisation in the Mount Isa Basin with hydrocarbons could not be overlooked. A comprehensive analysis of the available data suggests a link between the migration and possible generation or destruction of hydrocarbons and metal bearing fluids. Consequently, base metal exploration based on hydrocarbon exploration concepts is probably. the most effective technique in such basins. The metal-hydrocarbon-sedimentary basin-plate tectonic association (analogous to Phanerozoic models) is a compelling outcome of this work on the Palaeo- to Mesoproterozoic Mount lsa Basin. Petroleum within the Bowthom Block was apparently destroyed by hot brines that produced many ore deposits elsewhere in the basin.

Hash based disk imaging using AFF4

Forensic imaging has been facing scalability challenges for some time. As disk capacity growth continues to outpace storage IO bandwidth, the demands placed on storage and time are ever increasing. Data reduction and de-duplication technologies are now commonplace in the Enterprise space, and are potentially applicable to forensic acquisition. Using the new AFF4 forensic file format we employ a hash based compression scheme to leverage an existing corpus of images, reducing both acquisition time and storage requirements. This paper additionally describes some of the recent evolution in the AFF4 file format making the efficient implementation of hash based imaging a reality.

Vision-based classification of solder joint defects

Inspection of solder joints has been a critical process in the electronic manufacturing industry to reduce manufacturing cost, improve yield, and ensure product quality and reliability. The solder joint inspection problem is more challenging than many other visual inspections because of the variability in the appearance of solder joints. Although many research works and various techniques have been developed to classify defect in solder joints, these methods have complex systems of illumination for image acquisition and complicated classification algorithms. An important stage of the analysis is to select the right method for the classification. Better inspection technologies are needed to fill the gap between available inspection capabilities and industry systems. This dissertation aims to provide a solution that can overcome some of the limitations of current inspection techniques. This research proposes two inspection steps for automatic solder joint classification system. The “front-end” inspection system includes illumination normalisation, localization and segmentation. The illumination normalisation approach can effectively and efficiently eliminate the effect of uneven illumination while keeping the properties of the processed image. The “back-end” inspection involves the classification of solder joints by using Log Gabor filter and classifier fusion. Five different levels of solder quality with respect to the amount of solder paste have been defined. Log Gabor filter has been demonstrated to achieve high recognition rates and is resistant to misalignment. Further testing demonstrates the advantage of Log Gabor filter over both Discrete Wavelet Transform and Discrete Cosine Transform. Classifier score fusion is analysed for improving recognition rate. Experimental results demonstrate that the proposed system improves performance and robustness in terms of classification rates. This proposed system does not need any special illumination system, and the images are acquired by an ordinary digital camera. In fact, the choice of suitable features allows one to overcome the problem given by the use of non complex illumination systems. The new system proposed in this research can be incorporated in the development of an automated non-contact, non-destructive and low cost solder joint quality inspection system.

Unsupervised alignment of thousands of images

The task addressed in this thesis is the automatic alignment of an ensemble of misaligned images in an unsupervised manner. This application is especially useful in computer vision applications where annotations of the shape of an object of interest present in a collection of images is required. Performing this task manually is a slow, tedious, expensive and error prone process which hinders the progress of research laboratories and businesses. Most recently, the unsupervised removal of geometric variation present in a collection of images has been referred to as congealing based on the seminal work of Learned-Miller [21]. The only assumption made in congealing is that the parametric nature of the misalignment is known a priori (e.g. translation, similarity, a�ne, etc) and that the object of interest is guaranteed to be present in each image. The capability to congeal an ensemble of misaligned images stemming from the same object class has numerous applications in object recognition, detection and tracking. This thesis concerns itself with the construction of a congealing algorithm titled, least-squares congealing, which is inspired by the well known image to image alignment algorithm developed by Lucas and Kanade [24]. The algorithm is shown to have superior performance characteristics when compared to previously established methods: canonical congealing by Learned-Miller [21] and stochastic congealing by Z�ollei [39].

Digital constitutionalism and the role of the rule of law in the governance of virtual communities

This project proposes a new conceptual framework for the regulation of social networks and virtual communities. By applying a model based upon the rule of law, this thesis addresses the growing tensions that revolve around the public use of private networks. This research examines the shortcomings of traditional contractual governance models and cyberlaw theory and provides a reconstituted approach that will allow public constitutional-type interests to be recognised in the interpretation and enforcement of contractual doctrine.

Wide-baseline keypoint detection and matching with wide-angle images for vision based localisation

This thesis addresses the problem of detecting and describing the same scene points in different wide-angle images taken by the same camera at different viewpoints. This is a core competency of many vision-based localisation tasks including visual odometry and visual place recognition. Wide-angle cameras have a large field of view that can exceed a full hemisphere, and the images they produce contain severe radial distortion. When compared to traditional narrow field of view perspective cameras, more accurate estimates of camera egomotion can be found using the images obtained with wide-angle cameras. The ability to accurately estimate camera egomotion is a fundamental primitive of visual odometry, and this is one of the reasons for the increased popularity in the use of wide-angle cameras for this task. Their large field of view also enables them to capture images of the same regions in a scene taken at very different viewpoints, and this makes them suited for visual place recognition. However, the ability to estimate the camera egomotion and recognise the same scene in two different images is dependent on the ability to reliably detect and describe the same scene points, or ‘keypoints’, in the images. Most algorithms used for this purpose are designed almost exclusively for perspective images. Applying algorithms designed for perspective images directly to wide-angle images is problematic as no account is made for the image distortion. The primary contribution of this thesis is the development of two novel keypoint detectors, and a method of keypoint description, designed for wide-angle images. Both reformulate the Scale- Invariant Feature Transform (SIFT) as an image processing operation on the sphere. As the image captured by any central projection wide-angle camera can be mapped to the sphere, applying these variants to an image on the sphere enables keypoints to be detected in a manner that is invariant to image distortion. Each of the variants is required to find the scale-space representation of an image on the sphere, and they differ in the approaches they used to do this. Extensive experiments using real and synthetically generated wide-angle images are used to validate the two new keypoint detectors and the method of keypoint description. The best of these two new keypoint detectors is applied to vision based localisation tasks including visual odometry and visual place recognition using outdoor wide-angle image sequences. As part of this work, the effect of keypoint coordinate selection on the accuracy of egomotion estimates using the Direct Linear Transform (DLT) is investigated, and a simple weighting scheme is proposed which attempts to account for the uncertainty of keypoint positions during detection. A word reliability metric is also developed for use within a visual ‘bag of words’ approach to place recognition.