Heteroscedastic probabilistic linear discriminant analysis for manifold learning in video-based face recognition

To recognize faces in video, face appearances have been widely modeled as piece-wise local linear models which linearly approximate the smooth yet non-linear low dimensional face appearance manifolds. The choice of representations of the local models is crucial. Most of the existing methods learn each local model individually meaning that they only anticipate variations within each class. In this work, we propose to represent local models as Gaussian distributions which are learned simultaneously using the heteroscedastic probabilistic linear discriminant analysis (PLDA). Each gallery video is therefore represented as a collection of such distributions. With the PLDA, not only the within-class variations are estimated during the training, the separability between classes is also maximized leading to an improved discrimination. The heteroscedastic PLDA itself is adapted from the standard PLDA to approximate face appearance manifolds more accurately. Instead of assuming a single global within-class covariance, the heteroscedastic PLDA learns different within-class covariances specific to each local model. In the recognition phase, a probe video is matched against gallery samples through the fusion of point-to-model distances. Experiments on the Honda and MoBo datasets have shown the merit of the proposed method which achieves better performance than the state-of-the-art technique.

Improving opportunity recognition and business performance in small and medium manufacturing enterprises through design innovation programs

Increasing awareness of the benefits of stimulating entrepreneurial behaviour in small and medium enterprises has fostered strong interest in innovation programs. Recently many western countries have invested in design innovation for better firm performance. This research presents some early findings from a study of companies that participated in a holistic approach to design innovation, where the outcomes include better business performance and better market positioning in global markets. Preliminary findings from in-depth semi-structured interviews indicate the importance of firm openness to new ways of working and to developing new processes of strategic entrepreneurship. Implications for theory and practice are discussed.

How the environment affects opportunity recognition by entrepreneurs at the bottom of the pyramid

There is an army of bottom of the pyramid entrepreneurs (BOPE) who have the potential to transform developing economies, if they can identify and exploit business opportunities. BOPE could have unidentified resources that could lead to the recognition of radical new opportunities. This study paper asks how environmental factors and identification of resources affect Opportunity Recognition by BOP entrepreneurs in developing economies. To investigate this research question we conduct a literature review and plan semi-structured interviews of existing and nascent entrepreneurs in the largest and arguably the poorest country in Africa, the Democratic Republic of the Congo. In this paper we review the context of BOPE and describe the methodology we will use to gather and analyse data. Finally, we describe our access to suitable respondents for this study and how it will be conducted.

I-vector based speaker recognition using advanced channel compensation techniques

This paper investigates advanced channel compensation techniques for the purpose of improving i-vector speaker verification performance in the presence of high intersession variability using the NIST 2008 and 2010 SRE corpora. The performance of four channel compensation techniques: (a) weighted maximum margin criterion (WMMC), (b) source-normalized WMMC (SN-WMMC), (c) weighted linear discriminant analysis (WLDA), and; (d) source-normalized WLDA (SN-WLDA) have been investigated. We show that, by extracting the discriminatory information between pairs of speakers as well as capturing the source variation information in the development i-vector space, the SN-WLDA based cosine similarity scoring (CSS) i-vector system is shown to provide over 20% improvement in EER for NIST 2008 interview and microphone verification and over 10% improvement in EER for NIST 2008 telephone verification, when compared to SN-LDA based CSS i-vector system. Further, score-level fusion techniques are analyzed to combine the best channel compensation approaches, to provide over 8% improvement in DCF over the best single approach, (SN-WLDA), for NIST 2008 interview/ telephone enrolment-verification condition. Finally, we demonstrate that the improvements found in the context of CSS also generalize to state-of-the-art GPLDA with up to 14% relative improvement in EER for NIST SRE 2010 interview and microphone verification and over 7% relative improvement in EER for NIST SRE 2010 telephone verification.

Prostate gland and extra-capsular tissue 3D reconstruction and measurement

Currently there are little objective parameters that can quantify the success of one form of prostate surgical removal over another. Accordingly, at Old Dominion University (ODU) we have been developing a process resulting in the use of software algorithms to assess the coverage and depth of extra-capsular soft tissue removed with the prostate by the various surgical approaches. Parameters such as the percent of capsule that is bare of soft tissue and where present the depth and extent of coverage have been assessed. First, visualization methods and tools are developed for images of prostate slices that are provided to ODU by the Pathology Department at Eastern Virginia Medical School (EVMS). The visualization tools interpolate and present 3D models of the prostates. Measurement algorithms are then applied to determine statistics about extra-capsular tissue coverage. This paper addresses the modeling, visualization, and analysis of prostate gland tissue to aid in quantifying prostate surgery success. Particular attention is directed towards the accuracy of these measurements and is addressed in the analysis discussions.

Comparison between analytical and 3D finite element solutions for borehole stresses in anisotropic elastic rock

We present a rigorous validation of the analytical Amadei solution for the stress concentration around an arbitrarily orientated borehole in general anisotropic elastic media. First, we revisit the theoretical framework of the Amadei solution and present analytical insights that show that the solution does indeed contain all special cases of symmetry, contrary to previous understanding, provided that the reduced strain coefficients b11 and b55 are not equal. It is shown from theoretical considerations and published experimental data that the b11 and b55 are not equal for realistic rocks. Second, we develop a 3D finite element elastic model within a hybrid analytical–numerical workflow that circumvents the need to rebuild and remesh the model for every borehole and material orientation. Third, we show that the borehole stresses computed from the numerical model and the analytical solution match almost perfectly for different borehole orientations (vertical, deviated and horizontal) and for several cases involving isotropic, transverse isotropic and orthorhombic symmetries. It is concluded that the analytical Amadei solution is valid with no restriction on the borehole orientation or the symmetry of the elastic anisotropy.

3D thermal mapping of building interiors using an RGB-D and thermal camera

The building sector is the dominant consumer of energy and therefore a major contributor to anthropomorphic climate change. The rapid generation of photorealistic, 3D environment models with incorporated surface temperature data has the potential to improve thermographic monitoring of building energy efficiency. In pursuit of this goal, we propose a system which combines a range sensor with a thermal-infrared camera. Our proposed system can generate dense 3D models of environments with both appearance and temperature information, and is the first such system to be developed using a low-cost RGB-D camera. The proposed pipeline processes depth maps successively, forming an ongoing pose estimate of the depth camera and optimizing a voxel occupancy map. Voxels are assigned 4 channels representing estimates of their true RGB and thermal-infrared intensity values. Poses corresponding to each RGB and thermal-infrared image are estimated through a combination of timestamp-based interpolation and a pre-determined knowledge of the extrinsic calibration of the system. Raycasting is then used to color the voxels to represent both visual appearance using RGB, and an estimate of the surface temperature. The output of the system is a dense 3D model which can simultaneously represent both RGB and thermal-infrared data using one of two alternative representation schemes. Experimental results demonstrate that the system is capable of accurately mapping difficult environments, even in complete darkness.

Collaborative 3D BPMN Editor Two

Video presented as part of AMCIS 2010 conference in Lima Peru. New improved collaborative BPMN editor video, showing a new interface and collaboration capabilities via remote login of another avatar.

Collaborative 3D BPMN Editor

Video presented as part of ACIS 2009 conference in Melbourne Australia. This video outlines a collaborative BPMN editing system, developed by Stephen West, an IT Research Masters student at QUT, Brisbane, Australia. The editor uses a number of tools to facilitate collaborative process modelling, including a presentation wall, to view text descriptions of business processes, and a tile-based BPMN editor. We will post a video soon focussing on the multi-user capabilities of this editor. For more details see www.bpmve.org.

3D BPMN airport processes

Video presented as part of ACIS 2009 conference in Melbourne Australia. This movie is a demonstration of the use of 3D Virtual Environments to visualise 3D BPMN Process Models, and in particular, to highlight any issues with the process model that are spatial in nature. This work is part of a paper accepted for the Asia-Pacific Conference on Conceptual Modelling (APCCM 2010) to be held in Brisbane - http://2010.apccm.org/

Insect odour perception: recognition of odour components by flower foraging moths

Odours emitted by flowers are complex blends of volatile compounds. These odours are learnt by flower-visiting insect species, improving their recognition of rewarding flowers and thus foraging efficiency. We investigated the flexibility of floral odour learning by testing whether adult moths recognize single compounds common to flowers on which they forage. Dual choice preference tests on Helicoverpa armigera moths allowed free flying moths to forage on one of three flower species; Argyranthemum frutescens (federation daisy), Cajanus cajan (pigeonpea) or Nicotiana tabacum (tobacco). Results showed that, (i) a benzenoid (phenylacetaldehyde) and a monoterpene (linalool) were subsequently recognized after visits to flowers that emitted these volatile constituents, (ii) in a preference test, other monoterpenes in the flowers' odour did not affect the moths' ability to recognize the monoterpene linalool and (iii) relative preferences for two volatiles changed after foraging experience on a single flower species that emitted both volatiles. The importance of using free flying insects and real flowers to understand the mechanisms involved in floral odour learning in nature are discussed in the context of our findings.

Reconstructing 3D x-ray CT images of polymer gel dosimeters using the zero-scan method

In this study x-ray CT has been used to produce a 3D image of an irradiated PAGAT gel sample, with noise-reduction achieved using the ‘zero-scan’ method. The gel was repeatedly CT scanned and a linear fit to the varying Hounsfield unit of each pixel in the 3D volume was evaluated across the repeated scans, allowing a zero-scan extrapolation of the image to be obtained. To minimise heating of the CT scanner’s x-ray tube, this study used a large slice thickness (1 cm), to provide image slices across the irradiated region of the gel, and a relatively small number of CT scans (63), to extrapolate the zero-scan image. The resulting set of transverse images shows reduced noise compared to images from the initial CT scan of the gel, without being degraded by the additional radiation dose delivered to the gel during the repeated scanning. The full, 3D image of the gel has a low spatial resolution in the longitudinal direction, due to the selected scan parameters. Nonetheless, important features of the dose distribution are apparent in the 3D x-ray CT scan of the gel. The results of this study demonstrate that the zero-scan extrapolation method can be applied to the reconstruction of multiple x-ray CT slices, to provide useful 2D and 3D images of irradiated dosimetry gels.

Robust image hash functions using higher order spectra

Robust hashing is an emerging field that can be used to hash certain data types in applications unsuitable for traditional cryptographic hashing methods. Traditional hashing functions have been used extensively for data/message integrity, data/message authentication, efficient file identification and password verification. These applications are possible because the hashing process is compressive, allowing for efficient comparisons in the hash domain but non-invertible meaning hashes can be used without revealing the original data. These techniques were developed with deterministic (non-changing) inputs such as files and passwords. For such data types a 1-bit or one character change can be significant, as a result the hashing process is sensitive to any change in the input. Unfortunately, there are certain applications where input data are not perfectly deterministic and minor changes cannot be avoided. Digital images and biometric features are two types of data where such changes exist but do not alter the meaning or appearance of the input. For such data types cryptographic hash functions cannot be usefully applied. In light of this, robust hashing has been developed as an alternative to cryptographic hashing and is designed to be robust to minor changes in the input. Although similar in name, robust hashing is fundamentally different from cryptographic hashing. Current robust hashing techniques are not based on cryptographic methods, but instead on pattern recognition techniques. Modern robust hashing algorithms consist of feature extraction followed by a randomization stage that introduces non-invertibility and compression, followed by quantization and binary encoding to produce a binary hash output. In order to preserve robustness of the extracted features, most randomization methods are linear and this is detrimental to the security aspects required of hash functions. Furthermore, the quantization and encoding stages used to binarize real-valued features requires the learning of appropriate quantization thresholds. How these thresholds are learnt has an important effect on hashing accuracy and the mere presence of such thresholds are a source of information leakage that can reduce hashing security. This dissertation outlines a systematic investigation of the quantization and encoding stages of robust hash functions. While existing literature has focused on the importance of quantization scheme, this research is the first to emphasise the importance of the quantizer training on both hashing accuracy and hashing security. The quantizer training process is presented in a statistical framework which allows a theoretical analysis of the effects of quantizer training on hashing performance. This is experimentally verified using a number of baseline robust image hashing algorithms over a large database of real world images. This dissertation also proposes a new randomization method for robust image hashing based on Higher Order Spectra (HOS) and Radon projections. The method is non-linear and this is an essential requirement for non-invertibility. The method is also designed to produce features more suited for quantization and encoding. The system can operate without the need for quantizer training, is more easily encoded and displays improved hashing performance when compared to existing robust image hashing algorithms. The dissertation also shows how the HOS method can be adapted to work with biometric features obtained from 2D and 3D face images.

Automatic object segmentation of unstructured scenes using colour and depth maps

This study presents a segmentation pipeline that fuses colour and depth information to automatically separate objects of interest in video sequences captured from a quadcopter. Many approaches assume that cameras are static with known position, a condition which cannot be preserved in most outdoor robotic applications. In this study, the authors compute depth information and camera positions from a monocular video sequence using structure from motion and use this information as an additional cue to colour for accurate segmentation. The authors model the problem similarly to standard segmentation routines as a Markov random field and perform the segmentation using graph cuts optimisation. Manual intervention is minimised and is only required to determine pixel seeds in the first frame which are then automatically reprojected into the remaining frames of the sequence. The authors also describe an automated method to adjust the relative weights for colour and depth according to their discriminative properties in each frame. Experimental results are presented for two video sequences captured using a quadcopter. The quality of the segmentation is compared to a ground truth and other state-of-the-art methods with consistently accurate results.

Nonparametric semantic segmentation for 3D street scenes

In this paper we propose a method to generate a large scale and accurate dense 3D semantic map of street scenes. A dense 3D semantic model of the environment can significantly improve a number of robotic applications such as autonomous driving, navigation or localisation. Instead of using offline trained classifiers for semantic segmentation, our approach employs a data-driven, nonparametric method to parse scenes which easily scale to a large environment and generalise to different scenes. We use stereo image pairs collected from cameras mounted on a moving car to produce dense depth maps which are combined into a global 3D reconstruction using camera poses from stereo visual odometry. Simultaneously, 2D automatic semantic segmentation using a nonparametric scene parsing method is fused into the 3D model. Furthermore, the resultant 3D semantic model is improved with the consideration of moving objects in the scene. We demonstrate our method on the publicly available KITTI dataset and evaluate the performance against manually generated ground truth.