Feature-domain super-resolution framework for gabor-based face and iris recognition

The low resolution of images has been one of the major limitations in recognising humans from a distance using their biometric traits, such as face and iris. Superresolution has been employed to improve the resolution and the recognition performance simultaneously, however the majority of techniques employed operate in the pixel domain, such that the biometric feature vectors are extracted from a super-resolved input image. Feature-domain superresolution has been proposed for face and iris, and is shown to further improve recognition performance by capitalising on direct super-resolving the features which are used for recognition. However, current feature-domain superresolution approaches are limited to simple linear features such as Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA), which are not the most discriminant features for biometrics. Gabor-based features have been shown to be one of the most discriminant features for biometrics including face and iris. This paper proposes a framework to conduct super-resolution in the non-linear Gabor feature domain to further improve the recognition performance of biometric systems. Experiments have confirmed the validity of the proposed approach, demonstrating superior performance to existing linear approaches for both face and iris biometrics.

Probabilistic matching of image sets for video-based face recognition

We address the problem of face recognition on video by employing the recently proposed probabilistic linear discrimi-nant analysis (PLDA). The PLDA has been shown to be robust against pose and expression in image-based face recognition. In this research, the method is extended and applied to video where image set to image set matching is performed. We investigate two approaches of computing similarities between image sets using the PLDA: the closest pair approach and the holistic sets approach. To better model face appearances in video, we also propose the heteroscedastic version of the PLDA which learns the within-class covariance of each individual separately. Our experi-ments on the VidTIMIT and Honda datasets show that the combination of the heteroscedastic PLDA and the closest pair approach achieves the best performance.

On the application of the probabilistic linear discriminant analysis to face recognition across expression

Facial expression is one of the main issues of face recognition in uncontrolled environments. In this paper, we apply the probabilistic linear discriminant analysis (PLDA) method to recognize faces across expressions. Several PLDA approaches are tested and cross-evaluated on the Cohn-Kanade and JAFFE databases. With less samples per gallery subject, high recognition rates comparable to previous works have been achieved indicating the robustness of the approaches. Among the approaches, the mixture of PLDAs has demonstrated better performances. The experimental results also indicate that facial regions around the cheeks, eyes, and eyebrows are more discriminative than regions around the mouth, jaw, chin, and nose.

A quantum information retrieval approach to memory

As computers approach the physical limits of information storable in memory, new methods will be needed to further improve information storage and retrieval. We propose a quantum inspired vector based approach, which offers a contextually dependent mapping from the subsymbolic to the symbolic representations of information. If implemented computationally, this approach would provide exceptionally high density of information storage, without the traditionally required physical increase in storage capacity. The approach is inspired by the structure of human memory and incorporates elements of Gardenfors’ Conceptual Space approach and Humphreys et al.’s matrix model of memory.

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.

Documentary as history, memory, dream and film

A century ago, as the Western world embarked on a period of traumatic change, the visual realism of photography and documentary film brought print and radio news to life. The vision that these new mediums threw into stark relief was one of intense social and political upheaval: the birth of modernity fired and tempered in the crucible of the Great War. As millions died in this fiery chamber and the influenza pandemic that followed, lines of empires staggered to their fall, and new geo-political boundaries were scored in the raw, red flesh of Europe. The decade of 1910 to 1919 also heralded a prolific period of artistic experimentation. It marked the beginning of the social and artistic age of modernity and, with it, the nascent beginnings of a new art form: film. We still live in the shadow of this violent, traumatic and fertile age; haunted by the ghosts of Flanders and Gallipoli and its ripples of innovation and creativity. Something happened here, but to understand how and why is not easy; for the documentary images we carry with us in our collective cultural memory have become what Baudrillard refers to as simulacra. Detached from their referents, they have become referents themselves, to underscore other, grand narratives in television and Hollywood films. The personal histories of the individuals they represent so graphically–and their hope, love and loss–are folded into a national story that serves, like war memorials and national holidays, to buttress social myths and values. And, as filmic images cross-pollinate, with each iteration offering a new catharsis, events that must have been terrifying or wondrous are abstracted. In this paper we first discuss this transformation through reference to theories of documentary and memory–this will form a conceptual framework for a subsequent discussion of the short film Anmer. Produced by the first author in 2010, Anmer is a visual essay on documentary, simulacra and the symbolic narratives of history. Its form, structure and aesthetic speak of the confluence of documentary, history, memory and dream. Located in the first decade of the twentieth century, its non-linear narratives of personal tragedy and poetic dreamscapes are an evocative reminder of the distance between intimate experience, grand narratives, and the mythologies of popular films. This transformation of documentary sources not only played out in the processes of the film’s production, but also came to form its theme.

Evaluation of image resolution and super-resolution on face recognition performance

While researchers strive to improve automatic face recognition performance, the relationship between image resolution and face recognition performance has not received much attention. This relationship is examined systematically and a framework is developed such that results from super-resolution techniques can be compared. Three super-resolution techniques are compared with the Eigenface and Elastic Bunch Graph Matching face recognition engines. Parameter ranges over which these techniques provide better recognition performance than interpolated images is determined.

Saying sorry in the 21st century : public apologies in a digital world

The public apology to the Forgotten Australians in late 2009 was, for many, the culmination of a long campaign for recognition and justice. The groundswell for this apology was built through a series of submissions which documented the systemic institutionalised abuse and neglect experienced by the Forgotten Australians that has resulted, for some, in life-long disadvantage and marginalisation. Interestingly it seems that rather than the official documents being the catalyst for change and prompting this public apology, it was more often the personal stories of the Forgotten Australians that resonated and over time drew out quite a torrent of support from the public leading up to, during and after the public apology, just as had been the case with the ‘Stolen Generation.’ Research suggests (cite) that the ethics of such national apologies only make sense if their personal stories are seen as a collective responsibility of society, and only carry weight if we understand and seek to Nationally address the trauma experienced by such victims. In the case of the Forgotten Australians, the National Library of Australia’s Forgotten Australians and Former Child Migrants Oral History Project and the National Museum’s Inside project demonstrate commitment to the digitisation of the Forgotten Australians’ stories in order to promote a better public understanding of their experiences, and institutionally (and therefore formally) value them with renewed social importance. Our project builds on this work not by making or collecting more stories, but by examining the role of the internet and digital technologies used in the production and dissemination of individuals’ stories that have already been created during the period of time between the tabling of the senate inquiry, Children in Institutional Care (1999 or 2003?) and a formal National apology being delivered in Federal Parliament by PM Kevin Rudd (9 Nov, 2009?). This timeframe also represents the emergent first decade of Internet use by Australians, including the rapid easily accessible digital technologies and social media tools that were at our disposal, along with the promises the technology claimed to offer — that is that more people would benefit from the social connections these technologies allegedly were giving us.

PLDA based speaker recognition on short utterances

This paper investigates the effects of limited speech data in the context of speaker verification using a probabilistic linear discriminant analysis (PLDA) approach. Being able to reduce the length of required speech data is important to the development of automatic speaker verification system in real world applications. When sufficient speech is available, previous research has shown that heavy-tailed PLDA (HTPLDA) modeling of speakers in the i-vector space provides state-of-the-art performance, however, the robustness of HTPLDA to the limited speech resources in development, enrolment and verification is an important issue that has not yet been investigated. In this paper, we analyze the speaker verification performance with regards to the duration of utterances used for both speaker evaluation (enrolment and verification) and score normalization and PLDA modeling during development. Two different approaches to total-variability representation are analyzed within the PLDA approach to show improved performance in short-utterance mismatched evaluation conditions and conditions for which insufficient speech resources are available for adequate system development. The results presented within this paper using the NIST 2008 Speaker Recognition Evaluation dataset suggest that the HTPLDA system can continue to achieve better performance than Gaussian PLDA (GPLDA) as evaluation utterance lengths are decreased. We also highlight the importance of matching durations for score normalization and PLDA modeling to the expected evaluation conditions. Finally, we found that a pooled total-variability approach to PLDA modeling can achieve better performance than the traditional concatenated total-variability approach for short utterances in mismatched evaluation conditions and conditions for which insufficient speech resources are available for adequate system development.

Visual route recognition with a handful of bits

In this paper we use a sequence-based visual localization algorithm to reveal surprising answers to the question, how much visual information is actually needed to conduct effective navigation? The algorithm actively searches for the best local image matches within a sliding window of short route segments or 'sub-routes', and matches sub-routes by searching for coherent sequences of local image matches. In contract to many existing techniques, the technique requires no pre-training or camera parameter calibration. We compare the algorithm's performance to the state-of-the-art FAB-MAP 2.0 algorithm on a 70 km benchmark dataset. Performance matches or exceeds the state of the art feature-based localization technique using images as small as 4 pixels, fields of view reduced by a factor of 250, and pixel bit depths reduced to 2 bits. We present further results demonstrating the system localizing in an office environment with near 100% precision using two 7 bit Lego light sensors, as well as using 16 and 32 pixel images from a motorbike race and a mountain rally car stage. By demonstrating how little image information is required to achieve localization along a route, we hope to stimulate future 'low fidelity' approaches to visual navigation that complement probabilistic feature-based techniques.

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.