Dynamic visual features for audio-visual speaker verification

The cascading appearance-based (CAB) feature extraction technique has established itself as the state-of-the-art in extracting dynamic visual speech features for speech recognition. In this paper, we will focus on investigating the effectiveness of this technique for the related speaker verification application. By investigating the speaker verification ability of each stage of the cascade we will demonstrate that the same steps taken to reduce static speaker and environmental information for the visual speech recognition application also provide similar improvements for visual speaker recognition. A further study is conducted comparing synchronous HMM (SHMM) based fusion of CAB visual features and traditional perceptual linear predictive (PLP) acoustic features to show that higher complexity inherit in the SHMM approach does not appear to provide any improvement in the final audio-visual speaker verification system over simpler utterance level score fusion.

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.

Noise robust voice activity detection using features extracted from the time-domain autocorrelation function

This paper presents a method of voice activity detection (VAD) for high noise scenarios, using a noise robust voiced speech detection feature. The developed method is based on the fusion of two systems. The first system utilises the maximum peak of the normalised time-domain autocorrelation function (MaxPeak). The second zone system uses a novel combination of cross-correlation and zero-crossing rate of the normalised autocorrelation to approximate a measure of signal pitch and periodicity (CrossCorr) that is hypothesised to be noise robust. The score outputs by the two systems are then merged using weighted sum fusion to create the proposed autocorrelation zero-crossing rate (AZR) VAD. Accuracy of AZR was compared to state of the art and standardised VAD methods and was shown to outperform the best performing system with an average relative improvement of 24.8% in half-total error rate (HTER) on the QUT-NOISE-TIMIT database created using real recordings from high-noise environments.

Interactional competence in a paired speaking test : features salient to raters

Paired speaking tests are now commonly used in both high-stakes testing and classroom assessment contexts. The co-construction of discourse by candidates is regarded as a strength of paired speaking tests, as candidates have the opportunity to display a wider range of interactional competencies, including turn taking, initiating topics and engaging in extended discourse with a partner, rather than an examiner. However, the impact of the interlocutor in such jointly negotiated discourse and the implications for assessing interactional competence are areas of concern. This article reports on the features of interactional competence that were salient to four trained raters of 12 paired speaking tests through the analysis of rater notes, stimulated verbal recalls and rater discussions. Findings enabled the identification of features of the performance noted by raters when awarding scores for interactional competence, and the particular features associated with higher and lower scores. A number of these features were seen by the raters as mutual achievements, which raises the issue of the extent to which it is possible to assess individual contributions to the co-constructed performance. The findings have implications for defining the construct of interactional competence in paired speaking tests and operationalising this in rating scales.

Facial expression recognition using facial movement features

Facial expression is an important channel for human communication and can be applied in many real applications. One critical step for facial expression recognition (FER) is to accurately extract emotional features. Current approaches on FER in static images have not fully considered and utilized the features of facial element and muscle movements, which represent static and dynamic, as well as geometric and appearance characteristics of facial expressions. This paper proposes an approach to solve this limitation using ‘salient’ distance features, which are obtained by extracting patch-based 3D Gabor features, selecting the ‘salient’ patches, and performing patch matching operations. The experimental results demonstrate high correct recognition rate (CRR), significant performance improvements due to the consideration of facial element and muscle movements, promising results under face registration errors, and fast processing time. The comparison with the state-of-the-art performance confirms that the proposed approach achieves the highest CRR on the JAFFE database and is among the top performers on the Cohn-Kanade (CK) database.

Improving the performance of facial expression recognition using dynamic, subtle and regional features

Human facial expression is a complex process characterized of dynamic, subtle and regional emotional features. State-of-the-art approaches on facial expression recognition (FER) have not fully utilized this kind of features to improve the recognition performance. This paper proposes an approach to overcome this limitation using patch-based ‘salient’ Gabor features. A set of 3D patches are extracted to represent the subtle and regional features, and then inputted into patch matching operations for capturing the dynamic features. Experimental results show a significant performance improvement of the proposed approach due to the use of the dynamic features. Performance comparison with pervious work also confirms that the proposed approach achieves the highest CRR reported to date on the JAFFE database and a top-level performance on the Cohn-Kanade (CK) database.

Wide baseline correspondence extraction beyond local features

Robust, affine covariant, feature extractors provide a means to extract correspondences between images captured by widely separated cameras. Advances in wide baseline correspondence extraction require looking beyond the robust feature extraction and matching approach. This study examines new techniques of extracting correspondences that take advantage of information contained in affine feature matches. Methods of improving the accuracy of a set of putative matches, eliminating incorrect matches and extracting large numbers of additional correspondences are explored. It is assumed that knowledge of the camera geometry is not available and not immediately recoverable. The new techniques are evaluated by means of an epipolar geometry estimation task. It is shown that these methods enable the computation of camera geometry in many cases where existing feature extractors cannot produce sufficient numbers of accurate correspondences.

Crisis communication under transformative change : the emergent context and roles of primary and secondary organisations

In an era of complex challenges that draw sustained media attention and entangle multiple organisational actors, this thesis addresses the gap between current trends in society and business, and existing scholarship in public relations and crisis communication. By responding to calls from crisis communication researchers to develop theory (Coombs, 2006a), to examine the interdependencies of crises (Seeger, Sellnow, & Ulmer, 1998), and to consider variation in crisis response (Seeger, 2002), this thesis contributes to theory development in crisis communication and public relations. Through transformative change, this thesis extends existing scholarship built on a preservation or conservation logic where public relations is used to maintain stability by incrementally responding to changes in an organisation‘s environment (Cutlip, Center, & Broom, 2006; Everett, 2001; Grunig, 2000; Spicer, 1997). Based on the opportunity to contribute to ongoing theoretical development in the literature, the overall research problem guiding this thesis asks: How does transformative change during crisis influence corporate actors’ communication? This thesis adopts punctuated equilibrium theory, which describes change as alternating between long periods of stability and short periods of revolutionary or transformative change (Gersick, 1991; Romanelli & Tushman, 1994; Siggelkow, 2002; Tushman, Newman, & Romanelli, 1986; Tushman & Romanelli, 1985). As a theory for change, punctuated equilibrium provides an opportunity to examine public relations and transformative change, building on scholarship that is based primarily on incremental change. Further, existing scholarship in public relations and crisis communication focuses on the actions of single organisations in situational or short-term crisis events. Punctuated equilibrium theory enables the study of multiple crises and multiple organisational responses during transformative change. In doing so, punctuated equilibrium theory provides a framework to explain both the context for transformative change and actions or strategies enacted by organisations during transformative change (Tushman, Newman, & Romanelli, 1986; Tushman & Romanelli, 1985; Tushman, Virany, & Romanelli, 1986). The connections between context and action inform the research questions that guide this thesis: RQ1: What symbolic and substantive strategies persist and change as crises develop from situational events to transformative and multiple linked events? RQ2: What features of the crisis context influence changes in symbolic and substantive strategies? To shed light on these research questions, the thesis adopts a qualitative approach guided by process theory and methods to explicate the events, sequences and activities that were essential to change (Pettigrew, 1992; Van de Ven, 1992). Specifically, the thesis draws on an alternative template strategy (Langley, 1999) that provides several alternative interpretations of the same events (Allison, 1971; Allison & Zelikow, 1999). Following Allison (1971) and Allison and Zelikow (1999), this thesis uses three alternative templates of crisis or strategic response typologies to construct three narratives using media articles and organisational documents. The narratives are compared to identify and draw out different patterns of crisis communication strategies that operate within different crisis contexts. The thesis is based on the crisis events that affected three organisations within the pharmaceutical industry for four years. The primary organisation is Merck, as its product recall crisis triggered transformative change affecting, in different ways, the secondary organisations of Pfizer and Novartis. Three narratives are presented based on the crisis or strategic response typologies of Coombs (2006b), Allen and Caillouet (1994), and Oliver (1991). The findings of this thesis reveal different stories about crisis communication under transformative change. By zooming in to a micro perspective (Nicolini, 2009) to focus on the crisis communication and actions of a single organisation and zooming out to a macro perspective (Nicolini, 2009) to consider multiple organisations, new insights about crisis communication, change and the relationships among multiple organisations are revealed at context and action levels. At the context level, each subsequent narrative demonstrates greater connections among multiple corporate actors. By zooming out from Coombs‘ (2006b) focus on single organisations to consider Allen and Caillouet‘s (1994) integration of the web of corporate actors, the thesis demonstrates how corporate actors add accountability pressures to the primary organisation. Next, by zooming further out to the macro perspective by considering Oliver‘s (1991) strategic responses to institutional processes, the thesis reveals a greater range of corporate actors that are caught up in the process of transformative change and accounts for their varying levels of agency over their environment. By zooming in to a micro perspective and out to a macro perspective (Nicolini, 2009) across alternative templates, the thesis sheds light on sequences, events, and actions of primary and secondary organisations. Although the primary organisation remains the focus of sustained media attention across the four-year time frame, the secondary organisations, even when one faced a similar starting situation to the primary organisation, were buffered by the process of transformative change. This understanding of crisis contexts in transforming environments builds on existing knowledge in crisis communication. At the action level, the thesis also reveals different interpretations from each alternative template. Coombs‘ (2006b) narrative shows persistence in the primary organisation‘s crisis or strategic responses over the four-year time frame of the thesis. That is, the primary organisation consistently applies a diminish crisis response. At times, the primary organisation drew on denial responses when corporate actors questioned its legitimacy or actions. To close the crisis, the primary organisation uses a rebuild crisis posture (Coombs, 2006). These finding are replicated in Allen and Caillouet‘s (1994) narrative, noting this template‘s limitation to communication messages only. Oliver‘s (1991) narrative is consistent with Coombs‘ (2006b) but also demonstrated a shift from a strategic response that signals conformity to the environment to one that signals more active resistance to the environment over time. Specifically, the primary organisation‘s initial response demonstrates conformity but these same messages were used some three years later to set new expectations in the environment in order to shape criteria and build acceptance for future organisational decisions. In summary, the findings demonstrate the power of crisis or strategic responses when considered over time and in the context of transformative change. The conclusions of this research contribute to scholarship in the public relations and management literatures. Based on the significance of organisational theory, the primary contribution of the theory relates to the role of interorganisational linkages or legitimacy buffers that form during the punctuation of equilibrium. The network of linkages among the corporate actors are significant also to the crisis communication literature as they form part of the process model of crisis communication under punctuated equilibrium. This model extends existing research that focuses on crisis communication of single organisations to consider the emergent context that incorporates secondary organisations as well as the localised contests of legitimacy and buffers from regulatory authorities. The thesis also provides an empirical base for punctuated equilibrium in public relations and crisis communication, extending Murphy‘s (2000) introduction of the theory to the public relations literature. In doing this, punctuated equilibrium theory reinvigorates theoretical development in crisis communication by extending existing scholarship around incrementalist approaches and demonstrating how public relations works in the context of transformative change. Further research in this area could consider using alternative templates to study transformative change caused by a range of crisis types from natural disasters to product tampering, and to add further insight into the dynamics between primary and secondary organisations. This thesis contributes to practice by providing guidelines for crisis response strategy selection and indicators related to the emergent context for crises under transformative change that will help primary and secondary organisations‘ responses to crises.

Digit recognition using trispectral features

Features derived from the trispectra of DFT magnitude slices are used for multi-font digit recognition. These features are insensitive to translation, rotation, or scaling of the input. They are also robust to noise. Classification accuracy tests were conducted on a common data base of 256× 256 pixel bilevel images of digits in 9 fonts. Randomly rotated and translated noisy versions were used for training and testing. The results indicate that the trispectral features are better than moment invariants and affine moment invariants. They achieve a classification accuracy of 95% compared to about 81% for Hu's (1962) moment invariants and 39% for the Flusser and Suk (1994) affine moment invariants on the same data in the presence of 1% impulse noise using a 1-NN classifier. For comparison, a multilayer perceptron with no normalization for rotations and translations yields 34% accuracy on 16× 16 pixel low-pass filtered and decimated versions of the same data.

Postcode segmentation and recognition using projections and bispectral features

A system to segment and recognize Australian 4-digit postcodes from address labels on parcels is described. Images of address labels are preprocessed and adaptively thresholded to reduce noise. Projections are used to segment the line and then the characters comprising the postcode. Individual digits are recognized using bispectral features extracted from their parallel beam projections. These features are insensitive to translation, scaling and rotation, and robust to noise. Results on scanned images are presented. The system is currently being improved and implemented to work on-line.

On the behaviour of higher-order spectral features for object recognition in the presence of various types of noise

This paper presents results on the robustness of higher-order spectral features to Gaussian, Rayleigh, and uniform distributed noise. Based on cluster plots and accuracy results for various signal to noise conditions, the higher-order spectral features are shown to be better than moment invariant features.

Negative determinant of Hessian features

Local image feature extractors that select local maxima of the determinant of Hessian function have been shown to perform well and are widely used. This paper introduces the negative local minima of the determinant of Hessian function for local feature extraction. The properties and scale-space behaviour of these features are examined and found to be desirable for feature extraction. It is shown how this new feature type can be implemented along with the existing local maxima approach at negligible extra processing cost. Applications to affine covariant feature extraction and sub-pixel precise corner extraction are demonstrated. Experimental results indicate that the new corner detector is more robust to image blur and noise than existing methods. It is also accurate for a broader range of corner geometries. An affine covariant feature extractor is implemented by combining the minima of the determinant of Hessian with existing scale and shape adaptation methods. This extractor can be implemented along side the existing Hessian maxima extractor simply by finding both minima and maxima during the initial extraction stage. The minima features increase the number of correspondences by two to four fold. The additional minima features are very distinct from the maxima features in descriptor space and do not make the matching process more ambiguous.