Human identification from video using advanced gait recognition techniques

The solutions proposed in this thesis contribute to improve gait recognition performance in practical scenarios that further enable the adoption of gait recognition into real world security and forensic applications that require identifying humans at a distance. Pioneering work has been conducted on frontal gait recognition using depth images to allow gait to be integrated with biometric walkthrough portals. The effects of gait challenging conditions including clothing, carrying goods, and viewpoint have been explored. Enhanced approaches are proposed on segmentation, feature extraction, feature optimisation and classification elements, and state-of-the-art recognition performance has been achieved. A frontal depth gait database has been developed and made available to the research community for further investigation. Solutions are explored in 2D and 3D domains using multiple images sources, and both domain-specific and independent modality gait features are proposed.

Speaker verification using I-vector features

This PhD research has provided novel solutions to three major challenges which have prevented the wide spread deployment of speaker recognition technology: (1) combating enrolment/ verification mismatch, (2) reducing the large amount of development and training data that is required and (3) reducing the duration of speech required to verify a speaker. A range of applications of speaker recognition technology from forensics in criminal investigations to secure access in banking will benefit from the research outcomes.

Aspect-based opinion extraction from customer reviews

Text is the main method of communicating information in the digital age. Messages, blogs, news articles, reviews, and opinionated information abounds on the Internet. People commonly purchase products online and post their opinions about purchased items. This feedback is displayed publicly to assist others with their purchasing decisions, creating the need for a mechanism with which to extract and summarize useful information for enhancing the decision-making process. Our contribution is to improve the accuracy of extraction by combining different techniques from three major areas, named Data Mining, Natural Language Processing techniques and Ontologies. The proposed framework sequentially mines product’s aspects and users’ opinions, groups representative aspects by similarity, and generates an output summary. This paper focuses on the task of extracting product aspects and users’ opinions by extracting all possible aspects and opinions from reviews using natural language, ontology, and frequent “tag” sets. The proposed framework, when compared with an existing baseline model, yielded promising results.

Milling and diffusion extraction : theory and practice

AN ENGINEERING Workshop was held from 21 to 24 November 2006 in Veracruz, Mexico. Forty delegates from 12 countries attended the workshop on theory and practice of milling and diffusion extraction. This report provides a general overview of activities undertaken during that workshop which consisted of five technical sessions over two days with presentations and discussions plus two days of field and factory visits. Topics covered during the technical sessions included: power transmissions, cane preparation, diffusers, mills, and a comparison of milling and diffusion.

High-yeld RNA-extraction method for saliva

BACKGROUND: The use of salivary diagnostics is increasing because of its noninvasiveness, ease of sampling, and the relatively low risk of contracting infectious organisms. Saliva has been used as a biological fluid to identify and validate RNA targets in head and neck cancer patients. The goal of this study was to develop a robust, easy, and cost-effective method for isolating high yields of total RNA from saliva for downstream expression studies. METHODS: Oral whole saliva (200 mu L) was collected from healthy controls (n = 6) and from patients with head and neck cancer (n = 8). The method developed in-house used QIAzol lysis reagent (Qiagen) to extract RNA from saliva (both cell-free supernatants and cell pellets), followed by isopropyl alcohol precipitation, cDNA synthesis, and real-time PCR analyses for the genes encoding beta-actin ("housekeeping" gene) and histatin (a salivary gland-specific gene). RESULTS: The in-house QIAzol lysis reagent produced a high yield of total RNA (0.89 -7.1 mu g) from saliva (cell-free saliva and cell pellet) after DNase treatment. The ratio of the absorbance measured at 260 nm to that at 280 nm ranged from 1.6 to 1.9. The commercial kit produced a 10-fold lower RNA yield. Using our method with the QIAzol lysis reagent, we were also able to isolate RNA from archived saliva samples that had been stored without RNase inhibitors at -80 degrees C for >2 years. CONCLUSIONS: Our in-house QIAzol method is robust, is simple, provides RNA at high yields, and can be implemented to allow saliva transcriptomic studies to be translated into a clinical setting.

Automated power semiconductor switching performance feature extraction from experimental double-pulse waveform data

Double-pulse tests are commonly used as a method for assessing the switching performance of power semiconductor switches in a clamped inductive switching application. Data generated from these tests are typically in the form of sampled waveform data captured using an oscilloscope. In cases where it is of interest to explore a multi-dimensional parameter space and corresponding result space it is necessary to reduce the data into key performance metrics via feature extraction. This paper presents techniques for the extraction of switching performance metrics from sampled double-pulse waveform data. The reported techniques are applied to experimental data from characterisation of a cascode gate drive circuit applied to power MOSFETs.

An MRF based abnormal event detection approach using motion and appearance features

Abnormal event detection has attracted a lot of attention in the computer vision research community during recent years due to the increased focus on automated surveillance systems to improve security in public places. Due to the scarcity of training data and the definition of an abnormality being dependent on context, abnormal event detection is generally formulated as a data-driven approach where activities are modeled in an unsupervised fashion during the training phase. In this work, we use a Gaussian mixture model (GMM) to cluster the activities during the training phase, and propose a Gaussian mixture model based Markov random field (GMM-MRF) to estimate the likelihood scores of new videos in the testing phase. Further-more, we propose two new features: optical acceleration, and the histogram of optical flow gradients; to detect the presence of any abnormal objects and speed violations in the scene. We show that our proposed method outperforms other state of the art abnormal event detection algorithms on publicly available UCSD dataset.

Evaluation of features for leaf classification in challenging conditions

Fine-grained leaf classification has concentrated on the use of traditional shape and statistical features to classify ideal images. In this paper we evaluate the effectiveness of traditional hand-crafted features and propose the use of deep convolutional neural network (ConvNet) features. We introduce a range of condition variations to explore the robustness of these features, including: translation, scaling, rotation, shading and occlusion. Evaluations on the Flavia dataset demonstrate that in ideal imaging conditions, combining traditional and ConvNet features yields state-of-theart performance with an average accuracy of 97:3%�0:6% compared to traditional features which obtain an average accuracy of 91:2%�1:6%. Further experiments show that this combined classification approach consistently outperforms the best set of traditional features by an average of 5:7% for all of the evaluated condition variations.

Factors influencing robustness and effectiveness of conditional random fields in active learning frameworks

Active learning approaches reduce the annotation cost required by traditional supervised approaches to reach the same effectiveness by actively selecting informative instances during the learning phase. However, effectiveness and robustness of the learnt models are influenced by a number of factors. In this paper we investigate the factors that affect the effectiveness, more specifically in terms of stability and robustness, of active learning models built using conditional random fields (CRFs) for information extraction applications. Stability, defined as a small variation of performance when small variation of the training data or a small variation of the parameters occur, is a major issue for machine learning models, but even more so in the active learning framework which aims to minimise the amount of training data required. The factors we investigate are a) the choice of incremental vs. standard active learning, b) the feature set used as a representation of the text (i.e., morphological features, syntactic features, or semantic features) and c) Gaussian prior variance as one of the important CRFs parameters. Our empirical findings show that incremental learning and the Gaussian prior variance lead to more stable and robust models across iterations. Our study also demonstrates that orthographical, morphological and contextual features as a group of basic features play an important role in learning effective models across all iterations.

Achieving competence: The interactional features of children's storytelling

Early years researchers interested in storytelling have largely focused on the development of children’s language and social skills within constructed story sessions. Less focus has been given to the interactional aspects of storytelling in children’s everyday conversation and how the members themselves, the storytellers and story recipients, manage storytelling. An interactional view, using ethnomethodological and conversation analytic approaches, offers the opportunity to study children’s narratives in terms of ‘members work’. Detailed examination of a video-recorded interaction among a group of children in a preparatory year playground shows how the children managed interactions within conversational storytelling. Analyses highlight the ways in which children worked at gaining a turn and made a story tellable within a round of second stories. Investigating children’s competence-in-action ‘from within’, the findings from this research show how children invoke and accomplish competence through their interactions.

Identifying weak linear features with the "coalescing shortest path image transform"

The detection of line-like features in images finds many applications in microanalysis. Actin fibers, microtubules, neurites, pilis, DNA, and other biological structures all come up as tenuous curved lines in microscopy images. A reliable tracing method that preserves the integrity and details of these structures is particularly important for quantitative analyses. We have developed a new image transform called the "Coalescing Shortest Path Image Transform" with very encouraging properties. Our scheme efficiently combines information from an extensive collection of shortest paths in the image to delineate even very weak linear features. © Copyright Microscopy Society of America 2011.

An evaluation of the neocognitron

We describe a sequence of experiments investigating the strengths and limitations of Fukushima's neocognitron as a handwritten digit classifier. Using the results of these experiments as a foundation, we propose and evaluate improvements to Fukushima's original network in an effort to obtain higher recognition performance. The neocognitron's performance is shown to be strongly dependent on the choice of selectivity parameters and we present two methods to adjust these variables. Performance of the network under the more effective of the two new selectivity adjustment techniques suggests that the network fails to exploit the features that distinguish different classes of input data. To avoid this shortcoming, the network's final layer cells were replaced by a nonlinear classifier (a multilayer perceptron) to create a hybrid architecture. Tests of Fukushima's original system and the novel systems proposed in this paper suggest that it may be difficult for the neocognitron to achieve the performance of existing digit classifiers due to its reliance upon the supervisor's choice of selectivity parameters and training data. These findings pertain to Fukushima's implementation of the system and should not be seen as diminishing the practical significance of the concept of hierarchical feature extraction embodied in the neocognitron. © 1997 IEEE.

Accelerating taxonomic discovery through automated character extraction

This paper discusses the following key messages. Taxonomy is (and taxonomists are) more important than ever in times of global change. Taxonomic endeavour is not occurring fast enough: in 250 years since the creation of the Linnean Systema Naturae, only about 20% of Earth's species have been named. We need fundamental changes to the taxonomic process and paradigm to increase taxonomic productivity by orders of magnitude. Currently, taxonomic productivity is limited principally by the rate at which we capture and manage morphological information to enable species discovery. Many recent (and welcomed) initiatives in managing and delivering biodiversity information and accelerating the taxonomic process do not address this bottleneck. Development of computational image analysis and feature extraction methods is a crucial missing capacity needed to enable taxonomists to overcome the taxonomic impediment in a meaningful time frame. Copyright © 2009 Magnolia Press.

Using upper bounds on attainable discrimination to select discrete valued features

Selection of features that will permit accurate pattern classification is a difficult task. However, if a particular data set is represented by discrete valued features, it becomes possible to determine empirically the contribution that each feature makes to the discrimination between classes. This paper extends the discrimination bound method so that both the maximum and average discrimination expected on unseen test data can be estimated. These estimation techniques are the basis of a backwards elimination algorithm that can be use to rank features in order of their discriminative power. Two problems are used to demonstrate this feature selection process: classification of the Mushroom Database, and a real-world, pregnancy related medical risk prediction task - assessment of risk of perinatal death.

Feature selection using expected attainable discrimination

We propose expected attainable discrimination (EAD) as a measure to select discrete valued features for reliable discrimination between two classes of data. EAD is an average of the area under the ROC curves obtained when a simple histogram probability density model is trained and tested on many random partitions of a data set. EAD can be incorporated into various stepwise search methods to determine promising subsets of features, particularly when misclassification costs are difficult or impossible to specify. Experimental application to the problem of risk prediction in pregnancy is described.