Low cost multimodal facial recognition via kinect sensors

This paper presents a novel low cost 3D facial recognition using gaming sensors such as Kinect™. The paper describes the hardware, calibration and infrared noise and pattern interference challenges of integrating multiple Kinect sensors. The preliminary results show a promising trend for low cost solutions that can be populated in crowded facilities such as malls and airports.

Flash-floods : genre subversion and the abject erotic in Dorothy Porter’s The monkey’s mask and El Dorado

When discussing her verse novels, Dorothy Porter explicitly stated that she loved to ‘write bad’. This paper will argue that it was Porter’s engagement with the verse novel form and genre subversion, most notably seen with her detective and crime thriller verse novels The monkey’s mask and El Dorado, that allows for a destabilisation of traditionally established genre conventions, which in turn provide a narrative foundation for Porter’s use of abject erotic imagery.

In both The monkey’s mask and El Dorado there are several types of ‘bodies’ to be examined: the body of the verse narrative, the bodies of the characters subjected to crime, the body of poetry that is referred to as evidence, and the abject eroticised body. Extending upon the studies of Rose Lucas (1997) and Fleur Diamond (1999), this paper contends that it is Porter’s engagement with the abject erotic, as informed by Julia Kristeva’s (1982) theory of the abject and Johanna Blakley’s (1995) discussion of the abject in relation to eroticism, that allows Porter to subvert the phallocentric limitations upheld through the crime fiction genre and offer an alternative representation for lesbian sexuality and desire.

Evolution of a contagious cancer: epigenetic variation in devil facial tumour disease

The emergence of Devil Facial Tumour Disease (DFTD), a highly contagious cancer, is driving Tasmanian devils (Sarcophilus harrisii) to extinction. The cancer is a genetically and chromosomally stable clonal cell line which is transmitted by biting during social interactions. In the present study, we explore the Devil Facial Tumour (DFT) epigenome and the genes involved in DNA methylation homeostasis. We show that tumour cells have similar levels of methylation to peripheral nerves, the tissue from which DFTD originated. We did not observe any strain or region-specific epimutations. However, we revealed a significant increase in hypomethylation in DFT samples over time (p < 0.0001). We propose that loss of methylation is not because of a maintenance deficiency, as an upregulation of DNA methyltransferase 1 gene was observed in tumours compared with nerves (p < 0.005). Instead, we believe that loss of methylation is owing to active demethylation, supported by the temporal increase in MBD2 and MBD4 (p < 0.001). The implications of these changes on disease phenotypes need to be explored. Our work shows that DFTD should not be treated as a static entity, but rather as an evolving parasite with epigenetic plasticity. Understanding the role of epimutations in the evolution of this parasitic cancer will provide unique insights into the role of epigenetic plasticity in cancer evolution and progression in traditional cancers that arise and die with their hosts.

New insights into the role of MHC diversity in devil facial tumour disease

Devil facial tumour disease (DFTD) is a fatal contagious cancer that has decimated Tasmanian devil populations. The tumour has spread without invoking immune responses, possibly due to low levels of Major Histocompatibility Complex (MHC) diversity in Tasmanian devils. Animals from a region in north-western Tasmania have lower infection rates than those in the east of the state. This area is a genetic transition zone between sub-populations, with individuals from north-western Tasmania displaying greater diversity than eastern devils at MHC genes, primarily through MHC class I gene copy number variation. Here we test the hypothesis that animals that remain healthy and tumour free show predictable differences at MHC loci compared to animals that develop the disease.

Intelligent facial emotion recognition using a layered encoding cascade optimization model

In this research, we propose a facial expression recognition system with a layered encoding cascade optimization model. Since generating an effective facial representation is a vital step to the success of facial emotion recognition, a modified Local Gabor Binary Pattern operator is first employed to derive a refined initial face representation and we then propose two evolutionary algorithms for feature optimization including (i) direct similarity and (ii) Pareto-based feature selection, under the layered cascade model. The direct similarity feature selection considers characteristics within the same emotion category that give the minimum within-class variation while the Pareto-based feature optimization focuses on features that best represent each expression category and at the same time provide the most distinctions to other expressions. Both a neural network and an ensemble classifier with weighted majority vote are implemented for the recognition of seven expressions based on the selected optimized features. The ensemble model also automatically updates itself with the most recent concepts in the data. Evaluated with the Cohn-Kanade database, our system achieves the best accuracies when the ensemble classifier is applied, and outperforms other research reported in the literature with 96.8% for direct similarity based optimization and 97.4% for the Pareto-based feature selection. Cross-database evaluation with frontal images from the MMI database has also been conducted to further prove system efficiency where it achieves 97.5% for Pareto-based approach and 90.7% for direct similarity-based feature selection and outperforms related research for MMI. When evaluated with 90° side-view images extracted from the videos of the MMI database, the system achieves superior performances with >80% accuracies for both optimization algorithms. Experiments with other weighting and meta-learning combination methods for the construction of ensembles are also explored with our proposed ensemble showing great adpativity to new test data stream for cross-database evaluation. In future work, we aim to incorporate other filtering techniques and evolutionary algorithms into the optimization models to further enhance the recognition performance.

Experimental comparison of approaches for feature extraction of facial attributes

In this paper, we compare the effectiveness of widely used approaches for representation of facial features in face images. Feature extraction is performed on face images for representation of four facial attributes, namely gender, age, race, and expression, by using discrete wavelet transform (DWT), Gabor wavelet, scale-invariant feature transform, local binary pattern (LBP), and Eigenfaces. After feature extraction and dimension reduction, demographic and expression classification is performed to identify the most discriminating techniques for representation of facial features. Extensive experiments are performed using publicly available face databases, namely Yale, Face95 Essex, and Cohn-Kanade (CK+) databases. Experimental results show that DWT, LBP, and Gabor wavelet methods are robust to variations of illumination, facial expression, and geometric transformations. Experimental results also show that race and expression are more difficult to predict than gender and age.

The SLUGGS survey: a new mask design to reconstruct the stellar populations and kinematics of both inner and outer galaxy regions

Integral field unit spectrographs allow the 2D exploration of the kinematics and stellar populations of galaxies, although they are generally restricted to small fields-of-view. Using the large field-of-view of the DEIMOS multislit spectrograph on Keck and our Stellar Kinematics using Multiple Slits technique, we are able to extract sky-subtracted stellar light spectra to large galactocentric radii. Here, we present a new DEIMOS mask design named SuperSKiMS that explores large spatial scales without sacrificing high spatial sampling. We simulate a set of observations with such a mask design on the nearby galaxy NGC 1023, measuring stellar kinematics and metallicities out to where the galaxy surface brightness is orders of magnitude fainter than the sky. With this technique we also reproduce the results from literature integral field spectroscopy in the innermost galaxy regions. In particular, we use the simulated NGC 1023 kinematics to model its total mass distribution to large radii, obtaining comparable results with those from published integral field unit observation. Finally, from new spectra of NGC 1023, we obtain stellar 2D kinematics and metallicity distributions that show good agreement with integral field spectroscopy results in the overlapping regions. In particular, we do not find a significant offset between our Stellar Kinematics using Multiple Slits and the ATLAS3D stellar velocity dispersion at the same spatial locations.