Improved facial expression recognition via uni-hyperplane classification

Large margin learning approaches, such as support vector machines (SVM), have been successfully applied to numerous classification tasks, especially for automatic facial expression recognition. The risk of such approaches however, is their sensitivity to large margin losses due to the influence from noisy training examples and outliers which is a common problem in the area of affective computing (i.e., manual coding at the frame level is tedious so coarse labels are normally assigned). In this paper, we leverage the relaxation of the parallel-hyperplanes constraint and propose the use of modified correlation filters (MCF). The MCF is similar in spirit to SVMs and correlation filters, but with the key difference of optimizing only a single hyperplane. We demonstrate the superiority of MCF over current techniques on a battery of experiments.

Text mining in negative relevance feedback

It is a big challenge to clearly identify the boundary between positive and negative streams. Several attempts have used negative feedback to solve this challenge; however, there are two issues for using negative relevance feedback to improve the effectiveness of information filtering. The first one is how to select constructive negative samples in order to reduce the space of negative documents. The second issue is how to decide noisy extracted features that should be updated based on the selected negative samples. This paper proposes a pattern mining based approach to select some offenders from the negative documents, where an offender can be used to reduce the side effects of noisy features. It also classifies extracted features (i.e., terms) into three categories: positive specific terms, general terms, and negative specific terms. In this way, multiple revising strategies can be used to update extracted features. An iterative learning algorithm is also proposed to implement this approach on RCV1, and substantial experiments show that the proposed approach achieves encouraging performance.

A decision table method for randomness measurement

Data quality has become a major concern for organisations. The rapid growth in the size and technology of a databases and data warehouses has brought significant advantages in accessing, storing, and retrieving information. At the same time, great challenges arise with rapid data throughput and heterogeneous accesses in terms of maintaining high data quality. Yet, despite the importance of data quality, literature has usually condensed data quality into detecting and correcting poor data such as outliers, incomplete or inaccurate values. As a result, organisations are unable to efficiently and effectively assess data quality. Having an accurate and proper data quality assessment method will enable users to benchmark their systems and monitor their improvement. This paper introduces a granules mining for measuring the random degree of error data which will enable decision makers to conduct accurate quality assessment and allocate the most severe data, thereby providing an accurate estimation of human and financial resources for conducting quality improvement tasks.

A toolbox for animal call recognition

Monitoring the natural environment is increasingly important as habit degradation and climate change reduce theworld’s biodiversity.We have developed software tools and applications to assist ecologists with the collection and analysis of acoustic data at large spatial and temporal scales.One of our key objectives is automated animal call recognition, and our approach has three novel attributes. First, we work with raw environmental audio, contaminated by noise and artefacts and containing calls that vary greatly in volume depending on the animal’s proximity to the microphone. Second, initial experimentation suggested that no single recognizer could dealwith the enormous variety of calls. Therefore, we developed a toolbox of generic recognizers to extract invariant features for each call type. Third, many species are cryptic and offer little data with which to train a recognizer. Many popular machine learning methods require large volumes of training and validation data and considerable time and expertise to prepare. Consequently we adopt bootstrap techniques that can be initiated with little data and refined subsequently. In this paper, we describe our recognition tools and present results for real ecological problems.

Robust facial feature extraction and matching

Automated feature extraction and correspondence determination is an extremely important problem in the face recognition community as it often forms the foundation of the normalisation and database construction phases of many recognition and verification systems. This paper presents a completely automatic feature extraction system based upon a modified volume descriptor. These features form a stable descriptor for faces and are utilised in a reversible jump Markov chain Monte Carlo correspondence algorithm to automatically determine correspondences which exist between faces. The developed system is invariant to changes in pose and occlusion and results indicate that it is also robust to minor face deformations which may be present with variations in expression.

Multiple cameras for audio-visual speech recognition in an automotive environment

Audio-visualspeechrecognition, or the combination of visual lip-reading with traditional acoustic speechrecognition, has been previously shown to provide a considerable improvement over acoustic-only approaches in noisy environments, such as that present in an automotive cabin. The research presented in this paper will extend upon the established audio-visualspeechrecognition literature to show that further improvements in speechrecognition accuracy can be obtained when multiple frontal or near-frontal views of a speaker's face are available. A series of visualspeechrecognition experiments using a four-stream visual synchronous hidden Markov model (SHMM) are conducted on the four-camera AVICAR automotiveaudio-visualspeech database. We study the relative contribution between the side and central orientated cameras in improving visualspeechrecognition accuracy. Finally combination of the four visual streams with a single audio stream in a five-stream SHMM demonstrates a relative improvement of over 56% in word recognition accuracy when compared to the acoustic-only approach in the noisiest conditions of the AVICAR database.

An analytical tool that quantifies cellular morphology changes from three-dimensional fluorescence images

The most common software analysis tools available for measuring fluorescence images are for two-dimensional (2D) data that rely on manual settings for inclusion and exclusion of data points, and computer-aided pattern recognition to support the interpretation and findings of the analysis. It has become increasingly important to be able to measure fluorescence images constructed from three-dimensional (3D) datasets in order to be able to capture the complexity of cellular dynamics and understand the basis of cellular plasticity within biological systems. Sophisticated microscopy instruments have permitted the visualization of 3D fluorescence images through the acquisition of multispectral fluorescence images and powerful analytical software that reconstructs the images from confocal stacks that then provide a 3D representation of the collected 2D images. Advanced design-based stereology methods have progressed from the approximation and assumptions of the original model-based stereology(1) even in complex tissue sections(2). Despite these scientific advances in microscopy, a need remains for an automated analytic method that fully exploits the intrinsic 3D data to allow for the analysis and quantification of the complex changes in cell morphology, protein localization and receptor trafficking. Current techniques available to quantify fluorescence images include Meta-Morph (Molecular Devices, Sunnyvale, CA) and Image J (NIH) which provide manual analysis. Imaris (Andor Technology, Belfast, Northern Ireland) software provides the feature MeasurementPro, which allows the manual creation of measurement points that can be placed in a volume image or drawn on a series of 2D slices to create a 3D object. This method is useful for single-click point measurements to measure a line distance between two objects or to create a polygon that encloses a region of interest, but it is difficult to apply to complex cellular network structures. Filament Tracer (Andor) allows automatic detection of the 3D neuronal filament-like however, this module has been developed to measure defined structures such as neurons, which are comprised of dendrites, axons and spines (tree-like structure). This module has been ingeniously utilized to make morphological measurements to non-neuronal cells(3), however, the output data provide information of an extended cellular network by using a software that depends on a defined cell shape rather than being an amorphous-shaped cellular model. To overcome the issue of analyzing amorphous-shaped cells and making the software more suitable to a biological application, Imaris developed Imaris Cell. This was a scientific project with the Eidgenössische Technische Hochschule, which has been developed to calculate the relationship between cells and organelles. While the software enables the detection of biological constraints, by forcing one nucleus per cell and using cell membranes to segment cells, it cannot be utilized to analyze fluorescence data that are not continuous because ideally it builds cell surface without void spaces. To our knowledge, at present no user-modifiable automated approach that provides morphometric information from 3D fluorescence images has been developed that achieves cellular spatial information of an undefined shape (Figure 1). We have developed an analytical platform using the Imaris core software module and Imaris XT interfaced to MATLAB (Mat Works, Inc.). These tools allow the 3D measurement of cells without a pre-defined shape and with inconsistent fluorescence network components. Furthermore, this method will allow researchers who have extended expertise in biological systems, but not familiarity to computer applications, to perform quantification of morphological changes in cell dynamics.

Emergent participant interaction

Emergence has the potential to effect complex, creative or open-ended interactions and novel game-play. We report on research into an emergent interactive system. This investigates emergent user behaviors and experience through the creation and evaluation of an interactive system. The system is +-NOW, an augmented reality, tangible, interactive art system. The paper briefly describes the qualities of emergence and +-NOW before focusing on its evaluation. This was a qualitative study with 30 participants conducted in context. Data analysis followed Grounded Theory Methods. Coding schemes, induced from data and external literature are presented. Findings show that emergence occurred in over half of the participants. The nature of these emergent behaviors is discussed along with examples from the data. Other findings indicate that participants found interaction with the work satisfactory. Design strategies for facilitating satisfactory experience despite the often unpredictable character of emergence, are briefly reviewed and potential application areas for emergence are discussed.

Open in art, nature and emergence

The interactive art system +-now is modelled on the openness of the natural world. Emergent shapes constitute a novel method for facilitating this openness. With the art system as an example, the relationship between openness and emergence is discussed. Lastly, artist reflections from the creation of the work are presented. These describe the nature of open systems and how they may be created.

Emergence and the art system ‘plus minus now’

Emergence is discussed in the context of a practice-based study of interactive art and a new taxonomy of emergence is proposed. The interactive art system ‘plus minus now’ is described and its relationship to emergence is discussed. ‘Plus minus now’ uses a novel method for instantiating emergent shapes. A preliminary investigation of this art system has been conducted and reveals the creation of temporal compositions by a participant. These temporal compositions and the emergent shapes are described using the taxonomy of emergence. Characteristics of emergent interactions and the implications of designing for them are discussed.

Emergence in interactive art

This thesis is concerned with creating and evaluating interactive art systems that facilitate emergent participant experiences. For the purposes of this research, interactive art is the computer based arts involving physical participation from the audience, while emergence is when a new form or concept appears that was not directly implied by the context from which it arose. This emergent ‘whole’ is more than a simple sum of its parts. The research aims to develop understanding of the nature of emergent experiences that might arise during participant interaction with interactive art systems. It also aims to understand the design issues surrounding the creation of these systems. The approach used is Practice-based, integrating practice, evaluation and theoretical research. Practice used methods from Reflection-in-action and Iterative design to create two interactive art systems: Glass Pond and +-now. Creation of +-now resulted in a novel method for instantiating emergent shapes. Both art works were also evaluated in exploratory studies. In addition, a main study with 30 participants was conducted on participant interaction with +-now. These sessions were video recorded and participants were interviewed about their experience. Recordings were transcribed and analysed using Grounded theory methods. Emergent participant experiences were identified and classified using a taxonomy of emergence in interactive art. This taxonomy draws on theoretical research. The outcomes of this Practice-based research are summarised as follows. Two interactive art systems, where the second work clearly facilitates emergent interaction, were created. Their creation involved the development of a novel method for instantiating emergent shapes and it informed aesthetic and design issues surrounding interactive art systems for emergence. A taxonomy of emergence in interactive art was also created. Other outcomes are the evaluation findings about participant experiences, including different types of emergence experienced and the coding schemes produced during data analysis.

JFA based Speaker Recognition using Delta-Phase and MFCC features

This paper investigates the use of mel-frequency deltaphase (MFDP) features in comparison to, and in fusion with, traditional mel-frequency cepstral coefficient (MFCC) features within joint factor analysis (JFA) speaker verification. MFCC features, commonly used in speaker recognition systems, are derived purely from the magnitude spectrum, with the phase spectrum completely discarded. In this paper, we investigate if features derived from the phase spectrum can provide additional speaker discriminant information to the traditional MFCC approach in a JFA based speaker verification system. Results are presented which provide a comparison of MFCC-only, MFDPonly and score fusion of the two approaches within a JFA speaker verification approach. Based upon the results presented using the NIST 2008 Speaker Recognition Evaluation (SRE) dataset, we believe that, while MFDP features alone cannot compete with MFCC features, MFDP can provide complementary information that result in improved speaker verification performance when both approaches are combined in score fusion, particularly in the case of shorter utterances.

Timed and Probabilistic Automata for Automatic Animal Call Recognition

Automatic Call Recognition is vital for environmental monitoring. Patten recognition has been applied in automatic species recognition for years. However, few studies have applied formal syntactic methods to species call structure analysis. This paper introduces a novel method to adopt timed and probabilistic automata in automatic species recognition based upon acoustic components as the primitives. We demonstrate this through one kind of birds in Australia: Eastern Yellow Robin.

Kernel analysis on Grassmann manifolds for action recognition

Modelling video sequences by subspaces has recently shown promise for recognising human actions. Subspaces are able to accommodate the effects of various image variations and can capture the dynamic properties of actions. Subspaces form a non-Euclidean and curved Riemannian manifold known as a Grassmann manifold. Inference on manifold spaces usually is achieved by embedding the manifolds in higher dimensional Euclidean spaces. In this paper, we instead propose to embed the Grassmann manifolds into reproducing kernel Hilbert spaces and then tackle the problem of discriminant analysis on such manifolds. To achieve efficient machinery, we propose graph-based local discriminant analysis that utilises within-class and between-class similarity graphs to characterise intra-class compactness and inter-class separability, respectively. Experiments on KTH, UCF Sports, and Ballet datasets show that the proposed approach obtains marked improvements in discrimination accuracy in comparison to several state-of-the-art methods, such as the kernel version of affine hull image-set distance, tensor canonical correlation analysis, spatial-temporal words and hierarchy of discriminative space-time neighbourhood features.

Improved foreground detection via block-based classifier cascade with probabilistic decision integration

Background subtraction is a fundamental low-level processing task in numerous computer vision applications. The vast majority of algorithms process images on a pixel-by-pixel basis, where an independent decision is made for each pixel. A general limitation of such processing is that rich contextual information is not taken into account. We propose a block-based method capable of dealing with noise, illumination variations, and dynamic backgrounds, while still obtaining smooth contours of foreground objects. Specifically, image sequences are analyzed on an overlapping block-by-block basis. A low-dimensional texture descriptor obtained from each block is passed through an adaptive classifier cascade, where each stage handles a distinct problem. A probabilistic foreground mask generation approach then exploits block overlaps to integrate interim block-level decisions into final pixel-level foreground segmentation. Unlike many pixel-based methods, ad-hoc postprocessing of foreground masks is not required. Experiments on the difficult Wallflower and I2R datasets show that the proposed approach obtains on average better results (both qualitatively and quantitatively) than several prominent methods. We furthermore propose the use of tracking performance as an unbiased approach for assessing the practical usefulness of foreground segmentation methods, and show that the proposed approach leads to considerable improvements in tracking accuracy on the CAVIAR dataset.