Applying SVMs and weight-based factor analysis to unsupervised adaptation for speaker verification

This paper presents an extended study on the implementation of support vector machine(SVM) based speaker verification in systems that employ continuous progressive model adaptation using the weight-based factor analysis model. The weight-based factor analysis model compensates for session variations in unsupervised scenarios by incorporating trial confidence measures in the general statistics used in the inter-session variability modelling process. Employing weight-based factor analysis in Gaussian mixture models (GMM) was recently found to provide significant performance gains to unsupervised classification. Further improvements in performance were found through the integration of SVM-based classification in the system by means of GMM supervectors. This study focuses particularly on the way in which a client is represented in the SVM kernel space using single and multiple target supervectors. Experimental results indicate that training client SVMs using a single target supervector maximises performance while exhibiting a certain robustness to the inclusion of impostor training data in the model. Furthermore, the inclusion of low-scoring target trials in the adaptation process is investigated where they were found to significantly aid performance.

Evaluation of spectral and texture features for object-based vegetation species classification using Support Vector Machines

The use of appropriate features to characterize an output class or object is critical for all classification problems. This paper evaluates the capability of several spectral and texture features for object-based vegetation classification at the species level using airborne high resolution multispectral imagery. Image-objects as the basic classification unit were generated through image segmentation. Statistical moments extracted from original spectral bands and vegetation index image are used as feature descriptors for image objects (i.e. tree crowns). Several state-of-art texture descriptors such as Gray-Level Co-Occurrence Matrix (GLCM), Local Binary Patterns (LBP) and its extensions are also extracted for comparison purpose. Support Vector Machine (SVM) is employed for classification in the object-feature space. The experimental results showed that incorporating spectral vegetation indices can improve the classification accuracy and obtained better results than in original spectral bands, and using moments of Ratio Vegetation Index obtained the highest average classification accuracy in our experiment. The experiments also indicate that the spectral moment features also outperform or can at least compare with the state-of-art texture descriptors in terms of classification accuracy.

Ontology-based image annotation

With regard to the long-standing problem of the semantic gap between low-level image features and high-level human knowledge, the image retrieval community has recently shifted its emphasis from low-level features analysis to high-level image semantics extrac- tion. User studies reveal that users tend to seek information using high-level semantics. Therefore, image semantics extraction is of great importance to content-based image retrieval because it allows the users to freely express what images they want. Semantic content annotation is the basis for semantic content retrieval. The aim of image anno- tation is to automatically obtain keywords that can be used to represent the content of images. The major research challenges in image semantic annotation are: what is the basic unit of semantic representation? how can the semantic unit be linked to high-level image knowledge? how can the contextual information be stored and utilized for image annotation? In this thesis, the Semantic Web technology (i.e. ontology) is introduced to the image semantic annotation problem. Semantic Web, the next generation web, aims at mak- ing the content of whatever type of media not only understandable to humans but also to machines. Due to the large amounts of multimedia data prevalent on the Web, re- searchers and industries are beginning to pay more attention to the Multimedia Semantic Web. The Semantic Web technology provides a new opportunity for multimedia-based applications, but the research in this area is still in its infancy. Whether ontology can be used to improve image annotation and how to best use ontology in semantic repre- sentation and extraction is still a worth-while investigation. This thesis deals with the problem of image semantic annotation using ontology and machine learning techniques in four phases as below. 1) Salient object extraction. A salient object servers as the basic unit in image semantic extraction as it captures the common visual property of the objects. Image segmen- tation is often used as the �rst step for detecting salient objects, but most segmenta- tion algorithms often fail to generate meaningful regions due to over-segmentation and under-segmentation. We develop a new salient object detection algorithm by combining multiple homogeneity criteria in a region merging framework. 2) Ontology construction. Since real-world objects tend to exist in a context within their environment, contextual information has been increasingly used for improving object recognition. In the ontology construction phase, visual-contextual ontologies are built from a large set of fully segmented and annotated images. The ontologies are composed of several types of concepts (i.e. mid-level and high-level concepts), and domain contextual knowledge. The visual-contextual ontologies stand as a user-friendly interface between low-level features and high-level concepts. 3) Image objects annotation. In this phase, each object is labelled with a mid-level concept in ontologies. First, a set of candidate labels are obtained by training Support Vectors Machines with features extracted from salient objects. After that, contextual knowledge contained in ontologies is used to obtain the �nal labels by removing the ambiguity concepts. 4) Scene semantic annotation. The scene semantic extraction phase is to get the scene type by using both mid-level concepts and domain contextual knowledge in ontologies. Domain contextual knowledge is used to create scene con�guration that describes which objects co-exist with which scene type more frequently. The scene con�guration is represented in a probabilistic graph model, and probabilistic inference is employed to calculate the scene type given an annotated image. To evaluate the proposed methods, a series of experiments have been conducted in a large set of fully annotated outdoor scene images. These include a subset of the Corel database, a subset of the LabelMe dataset, the evaluation dataset of localized semantics in images, the spatial context evaluation dataset, and the segmented and annotated IAPR TC-12 benchmark.

Developments in texture-based vector field visualisation techniques

Vector field visualisation is one of the classic sub-fields of scientific data visualisation. The need for effective visualisation of flow data arises in many scientific domains ranging from medical sciences to aerodynamics. Though there has been much research on the topic, the question of how to communicate flow information effectively in real, practical situations is still largely an unsolved problem. This is particularly true for complex 3D flows. In this presentation we give a brief introduction and background to vector field visualisation and comment on the effectiveness of the most common solutions. We will then give some examples of current development on texture-based techniques, and given practical examples of their use in CFD research and hydrodynamic applications.

A criminological analysis : using real-time monitoring to gather data on online predators

The Internet presents a constantly evolving frontier for criminology and policing, especially in relation to online predators – paedophiles operating within the Internet for safer access to children, child pornography and networking opportunities with other online predators. The goals of this qualitative study are to undertake behavioural research – identify personality types and archetypes of online predators and compare and contrast them with behavioural profiles and other psychological research on offline paedophiles and sex offenders. It is also an endeavour to gather intelligence on the technological utilisation of online predators and conduct observational research on the social structures of online predator communities. These goals were achieved through the covert monitoring and logging of public activity within four Internet Relay Chat(rooms) (IRC) themed around child sexual abuse and which were located on the Undernet network. Five days of monitoring was conducted on these four chatrooms between Wednesday 1 to Sunday 5 April 2009; this raw data was collated and analysed. The analysis identified four personality types – the gentleman predator, the sadist, the businessman and the pretender – and eight archetypes consisting of the groomers, dealers, negotiators, roleplayers, networkers, chat requestors, posters and travellers. The characteristics and traits of these personality types and archetypes, which were extracted from the literature dealing with offline paedophiles and sex offenders, are detailed and contrasted against the online sexual predators identified within the chatrooms, revealing many similarities and interesting differences particularly with the businessman and pretender personality types. These personality types and archetypes were illustrated by selecting users who displayed the appropriate characteristics and tracking them through the four chatrooms, revealing intelligence data on the use of proxies servers – especially via the Tor software – and other security strategies such as Undernet’s host masking service. Name and age changes, which is used as a potential sexual grooming tactic was also revealed through the use of Analyst’s Notebook software and information on ISP information revealed the likelihood that many online predators were not using any safety mechanism and relying on the anonymity of the Internet. The activities of these online predators were analysed, especially in regards to child sexual grooming and the ‘posting’ of child pornography, which revealed a few of the methods in which online predators utilised new Internet technologies to sexually groom and abuse children – using technologies such as instant messengers, webcams and microphones – as well as store and disseminate illegal materials on image sharing websites and peer-to-peer software such as Gigatribe. Analysis of the social structures of the chatrooms was also carried out and the community functions and characteristics of each chatroom explored. The findings of this research have indicated several opportunities for further research. As a result of this research, recommendations are given on policy, prevention and response strategies with regards to online predators.

A methodology for object identification and tracking in construction based on spatial modeling and image matching techniques

Understanding the motion characteristics of on-site objects is desirable for the analysis of construction work zones, especially in problems related to safety and productivity studies. This article presents a methodology for rapid object identification and tracking. The proposed methodology contains algorithms for spatial modeling and image matching. A high-frame-rate range sensor was utilized for spatial data acquisition. The experimental results indicated that an occupancy grid spatial modeling algorithm could quickly build a suitable work zone model from the acquired data. The results also showed that an image matching algorithm is able to find the most similar object from a model database and from spatial models obtained from previous scans. It is then possible to use the matched information to successfully identify and track objects.

Modeling object identification and tracking errors on image-based safety assessment of earthmoving operations

Object identification and tracking have become critical for automated on-site construction safety assessment. The primary objective of this paper is to present the development of a testbed to analyze the impact of object identification and tracking errors caused by data collection devices and algorithms used for safety assessment. The testbed models workspaces for earthmoving operations and simulates safety-related violations, including speed limit violations, access violations to dangerous areas, and close proximity violations between heavy machinery. Three different cases were analyzed based on actual earthmoving operations conducted at a limestone quarry. Using the testbed, the impacts of device and algorithm errors were investigated for safety planning purposes.

Analysis of build-up of heavy metals and volatile organics on urban roads in Gold Coast, Australia

Urban water quality can be significantly impaired by the build-up of pollutants such as heavy metals and volatile organics on urban road surfaces due to vehicular traffic. Any control strategy for the mitigation of traffic related build-up of heavy metals and volatile organic pollutants should be based on the knowledge of their build-up processes. In the study discussed in this paper, the outcomes of a detailed experiment investigation into build-up processes of heavy metals and volatile organics are presented. It was found that traffic parameters such as average daily traffic, volume over capacity ratio and surface texture depth had similar strong correlations with the build-up of heavy metals and volatile organics. Multicriteria decision analyses revealed that the 1 - 74 um particulate fraction of total suspended solids (TSS) could be regarded as a surrogate indicator for particulate heavy metals in build-up and this same fraction of total organic carbon could be regarded as a surrogate indicator for particulate volatile organics build-up. In terms of pollutants affinity, TSS was found to be the predominant parameter for particulate heavy metals build-up and total dissolved solids was found to be the predominant parameter for he potential dissolved particulate fraction in heavy metals build-up. It was also found that land use did not play a significant role in the build-up of traffic generated heavy metals and volatile organics.

Image-based safety assessment : automated spatial safety risk identification of earthmoving and surface mining activities

This paper presents an automated image‐based safety assessment method for earthmoving and surface mining activities. The literature review revealed the possible causes of accidents on earthmoving operations, investigated the spatial risk factors of these types of accident, and identified spatial data needs for automated safety assessment based on current safety regulations. Image‐based data collection devices and algorithms for safety assessment were then evaluated. Analysis methods and rules for monitoring safety violations were also discussed. The experimental results showed that the safety assessment method collected spatial data using stereo vision cameras, applied object identification and tracking algorithms, and finally utilized identified and tracked object information for safety decision making.

Design of a preliminary error impact analysis model for spatial safety assessment of earthmoving operations

Regardless of technology benefits, safety planners still face difficulties explaining errors related to the use of different technologies and evaluating how the errors impact the performance of safety decision making. This paper presents a preliminary error impact analysis testbed to model object identification and tracking errors caused by image-based devices and algorithms and to analyze the impact of the errors for spatial safety assessment of earthmoving and surface mining activities. More specifically, this research designed a testbed to model workspaces for earthmoving operations, to simulate safety-related violations, and to apply different object identification and tracking errors on the data collected and processed for spatial safety assessment. Three different cases were analyzed based on actual earthmoving operations conducted at a limestone quarry. Using the testbed, the impacts of the errors were investigated for the safety planning purpose.

Comparison of standard image segmentation methods for segmentation of brain tumors from 2D MR images

In the analysis of medical images for computer-aided diagnosis and therapy, segmentation is often required as a preliminary step. Medical image segmentation is a complex and challenging task due to the complex nature of the images. The brain has a particularly complicated structure and its precise segmentation is very important for detecting tumors, edema, and necrotic tissues in order to prescribe appropriate therapy. Magnetic Resonance Imaging is an important diagnostic imaging technique utilized for early detection of abnormal changes in tissues and organs. It possesses good contrast resolution for different tissues and is, thus, preferred over Computerized Tomography for brain study. Therefore, the majority of research in medical image segmentation concerns MR images. As the core juncture of this research a set of MR images have been segmented using standard image segmentation techniques to isolate a brain tumor from the other regions of the brain. Subsequently the resultant images from the different segmentation techniques were compared with each other and analyzed by professional radiologists to find the segmentation technique which is the most accurate. Experimental results show that the Otsu’s thresholding method is the most suitable image segmentation method to segment a brain tumor from a Magnetic Resonance Image.

Analysis of micro-structural changes and measurement of their parameters of a food material

Food microstructure represents the way their elements arrangement and their interaction. Researchers in this field benefit from identifying new methods of examination of the microstructure and analysing the images. Experiments were undertaken to study micro-structural changes of food material during drying. Micro-structural images were obtained for potato samples of cubical shape at different moisture contents during drying using scanning electron microscopy. Physical parameters such as cell wall perimeter, and area were calculated using an image identification algorithm, based on edge detection and morphological operators. The algorithm was developed using Matlab.

Spectral–texture feature extraction using statistical moments with application to object-based vegetation species classification

The use of appropriate features to characterise an output class or object is critical for all classification problems. In order to find optimal feature descriptors for vegetation species classification in a power line corridor monitoring application, this article evaluates the capability of several spectral and texture features. A new idea of spectral–texture feature descriptor is proposed by incorporating spectral vegetation indices in statistical moment features. The proposed method is evaluated against several classic texture feature descriptors. Object-based classification method is used and a support vector machine is employed as the benchmark classifier. Individual tree crowns are first detected and segmented from aerial images and different feature vectors are extracted to represent each tree crown. The experimental results showed that the proposed spectral moment features outperform or can at least compare with the state-of-the-art texture descriptors in terms of classification accuracy. A comprehensive quantitative evaluation using receiver operating characteristic space analysis further demonstrates the strength of the proposed feature descriptors.

Evaluation of texture and geometry for dimensional facial expression recognition

Facial expression recognition (FER) algorithms mainly focus on classification into a small discrete set of emotions or representation of emotions using facial action units (AUs). Dimensional representation of emotions as continuous values in an arousal-valence space is relatively less investigated. It is not fully known whether fusion of geometric and texture features will result in better dimensional representation of spontaneous emotions. Moreover, the performance of many previously proposed approaches to dimensional representation has not been evaluated thoroughly on publicly available databases. To address these limitations, this paper presents an evaluation framework for dimensional representation of spontaneous facial expressions using texture and geometric features. SIFT, Gabor and LBP features are extracted around facial fiducial points and fused with FAP distance features. The CFS algorithm is adopted for discriminative texture feature selection. Experimental results evaluated on the publicly accessible NVIE database demonstrate that fusion of texture and geometry does not lead to a much better performance than using texture alone, but does result in a significant performance improvement over geometry alone. LBP features perform the best when fused with geometric features. Distributions of arousal and valence for different emotions obtained via the feature extraction process are compared with those obtained from subjective ground truth values assigned by viewers. Predicted valence is found to have a more similar distribution to ground truth than arousal in terms of covariance or Bhattacharya distance, but it shows a greater distance between the means.

Improved image quality for x-ray CT imaging of gel dosimeters

Purpose: This study provides a simple method for improving precision of x-ray computed tomography (CT) scans of irradiated polymer gel dosimetry. The noise affecting CT scans of irradiated gels has been an impediment to the use of clinical CT scanners for gel dosimetry studies. Method: In this study, it is shown that multiple scans of a single PAGAT gel dosimeter can be used to extrapolate a ‘zero-scan’ image which displays a similar level of precision to an image obtained by averaging multiple CT images, without the compromised dose measurement resulting from the exposure of the gel to radiation from the CT scanner. Results: When extrapolating the zero-scan image, it is shown that exponential and simple linear fits to the relationship between Hounsfield unit and scan number, for each pixel in the image, provides an accurate indication of gel density. Conclusions: It is expected that this work will be utilised in the analysis of three-dimensional gel volumes irradiated using complex radiotherapy treatments.