On-line learning of mutually orthogonal subspaces for face recognition by image sets.

We address the problem of face recognition by matching image sets. Each set of face images is represented by a subspace (or linear manifold) and recognition is carried out by subspace-to-subspace matching. In this paper, 1) a new discriminative method that maximises orthogonality between subspaces is proposed. The method improves the discrimination power of the subspace angle based face recognition method by maximizing the angles between different classes. 2) We propose a method for on-line updating the discriminative subspaces as a mechanism for continuously improving recognition accuracy. 3) A further enhancement called locally orthogonal subspace method is presented to maximise the orthogonality between competing classes. Experiments using 700 face image sets have shown that the proposed method outperforms relevant prior art and effectively boosts its accuracy by online learning. It is shown that the method for online learning delivers the same solution as the batch computation at far lower computational cost and the locally orthogonal method exhibits improved accuracy. We also demonstrate the merit of the proposed face recognition method on portal scenarios of multiple biometric grand challenge.

Modified Kanerva model. Results for real time word recognition

This paper describes results obtained using the modified Kanerva model to perform word recognition in continuous speech after being trained on the multi-speaker Alvey 'Hotel' speech corpus. Theoretical discoveries have recently enabled us to increase the speed of execution of part of the model by two orders of magnitude over that previously reported by Prager & Fallside. The memory required for the operation of the model has been similarly reduced. The recognition accuracy reaches 95% without syntactic constraints when tested on different data from seven trained speakers. Real time simulation of a model with 9,734 active units is now possible in both training and recognition modes using the Alvey PARSIFAL transputer array. The modified Kanerva model is a static network consisting of a fixed nonlinear mapping (location matching) followed by a single layer of conventional adaptive links. A section of preprocessed speech is transformed by the non-linear mapping to a high dimensional representation. From this intermediate representation a simple linear mapping is able to perform complex pattern discrimination to form the output, indicating the nature of the speech features present in the input window.

Face recognition from video

In spite of over two decades of intense research, illumination and pose invariance remain prohibitively challenging aspects of face recognition for most practical applications. The objective of this work is to recognize faces using video sequences both for training and recognition input, in a realistic, unconstrained setup in which lighting, pose and user motion pattern have a wide variability and face images are of low resolution. In particular there are three areas of novelty: (i) we show how a photometric model of image formation can be combined with a statistical model of generic face appearance variation, learnt offline, to generalize in the presence of extreme illumination changes; (ii) we use the smoothness of geodesically local appearance manifold structure and a robust same-identity likelihood to achieve invariance to unseen head poses; and (iii) we introduce an accurate video sequence "reillumination" algorithm to achieve robustness to face motion patterns in video. We describe a fully automatic recognition system based on the proposed method and an extensive evaluation on 171 individuals and over 1300 video sequences with extreme illumination, pose and head motion variation. On this challenging data set our system consistently demonstrated a nearly perfect recognition rate (over 99.7%), significantly outperforming state-of-the-art commercial software and methods from the literature. © Springer-Verlag Berlin Heidelberg 2006.

Developing a framework for mapping industrial emergence

The industrial landscape is becoming increasingly complex and dynamic, with innovative technologies stimulating the emergence of new industries and business models. This paper presents a preliminary framework for mapping industrial emergence, based on roadmapping principles, in order to understand the nature and characteristics of such phenomena. The focus at this stage is on historical examples of industrial emergence, with the preliminary framework based on observations from 20 'quick scan' maps, one of which is used to illustrate the framework. The learning from these historical cases, combined with further industrial consultation and literature review, will be used to develop practical methods for strategy and policy application. The paper concludes by summarising key learning points and further work needed to achieve these outcomes. © 2009 PICMET.

The dynamics of industrial emergence

The need to stimulate, identify and nurture new industries is a prominent challenge in advanced economies. While basic science represents a valuable source of new ideas and opportunities, it can often take decades before this science finally finds application in the market. While numerous studies have to date focused on aspects of industrial evolution, (e.g. innovation, internationalisation, new product introduction, technological lifecycles and emerging technologies), far fewer have focused on technology-based industrial emergence. It is clear that if assistance is to be provided to firms and industrial policymakers attempting to navigate industrial emergence then we need an improved understanding of the characteristics and dynamics of this phenomenon. Accordingly, this paper reviews published work from a range of disparate disciplines - evolutionary theory, social construction of technology (SCOT), complexity science, industrial dynamics and technology management - to identify these dynamics. Through this review we conceptualise industrial emergence as a co-evolutionary process in which nonlinear dynamics operate. Industrial emergence is sensitive to the initial availability of resources and the market applications, with growth dependent on the supply-demand coupling, agents' actions to reduce uncertainty and catalytic events. Through synthesizing these key dynamics we go on to propose a conceptual model for industrial emergence. © 2010 IEEE.

The Cambridge Manufacturing Leaders' Programme

As with all Cambridge teaching, the Cambridge Manufacturing Leaders' Programme is based on one-to-one tutorial supervision, comprising guidance throughout a major strategic development project in the programme participant's company, interspersed with reflective study time spent in Cambridge. In this paper a description of the course is set in a wider philosophical context, looking at the role of work in a personal developmental sense, and the responsibility carried by manufacturing leaders for shaping and guiding that process. It is shown that the programme is rooted in and embodies important aspects of our European heritage regarding work as a learning process and the master/apprentice relationship as a way of giving educational guidance.

Statistical parametric speech synthesis based on speaker and language factorization

An increasingly common scenario in building speech synthesis and recognition systems is training on inhomogeneous data. This paper proposes a new framework for estimating hidden Markov models on data containing both multiple speakers and multiple languages. The proposed framework, speaker and language factorization, attempts to factorize speaker-/language-specific characteristics in the data and then model them using separate transforms. Language-specific factors in the data are represented by transforms based on cluster mean interpolation with cluster-dependent decision trees. Acoustic variations caused by speaker characteristics are handled by transforms based on constrained maximum-likelihood linear regression. Experimental results on statistical parametric speech synthesis show that the proposed framework enables data from multiple speakers in different languages to be used to: train a synthesis system; synthesize speech in a language using speaker characteristics estimated in a different language; and adapt to a new language. © 2012 IEEE.

Two is better than one: Distinct roles for familiarity and recollection in retrieving palimpsest memories

Storing a new pattern in a palimpsest memory system comes at the cost of interfering with the memory traces of previously stored items. Knowing the age of a pattern thus becomes critical for recalling it faithfully. This implies that there should be a tight coupling between estimates of age, as a form of familiarity, and the neural dynamics of recollection, something which current theories omit. Using a normative model of autoassociative memory, we show that a dual memory system, consisting of two interacting modules for familiarity and recollection, has best performance for both recollection and recognition. This finding provides a new window onto actively contentious psychological and neural aspects of recognition memory.

Is UK Planning a Barrier to Energy Efficient Heritage Retrofit: A Comparative Analysis of a Selection of London Boroughs

This paper is part of a larger PhD research project examining the apparent conflict in UK planning between energy efficiency and conservation for the retrofit of the thermal envelope of the existing building stock. Review of the literature shows that the UK will not meet its 2050 emission reduction target without substantial improvement to the energy performance of the thermal envelope of the existing building stock and that significantly, 40% of the existing stock has heritage status and may be exempted from Building Regulations. A review of UK policy and legislation shows that there are clear national priorities towards reducing emissions and addressing climate change, yet also shows a movement towards local decision making and control. This paper compares the current status of thirteen London Boroughs in respect to their position on thermal envelope retrofit for heritage and traditionally constructed buildings. Data collection is through ongoing surveys and interviews that compare statistical data, planning policies, sustainability and environmental priorities, and Officer decision-making. This paper finds that there is a lack of consistency in application of planning policy across Boroughs and suggests that this is a barrier to the up-take of energy efficient retrofit. Various recommendations are suggested at both national and local level which could help UK planning and planning officers deliver more energy efficient heritage retrofits.