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.

Improving communication in design: Recommendations from the literature

Communication permeates every aspect of an engineer's work-from clarifying product specifications to shaping social ties. This paper offers an overview of recommendations from literature to improve communication within and among engineering teams. We assume communication problems are often the outcome of underlying factors and that it is fruitful to study and improve these influences. Having been empirically elicited in prior research, 24 factors considered in this paper include, e.g., availability of information about product specifications, roles and responsibilities, and overview of sequence of tasks. To improve these factors in order to enable effective communication, this paper collates more than hundred recommendations from journal articles and textbooks published in the fields of engineering design, management science, sociology, and psychology. Recommendations include, for example, identify priorities through risk and bottleneck analysis, give clear descriptions and role expectations, and employ effective process modeling tools. Contributions of this paper are a list of recommendations for industry practitioners and an effort-benefit evaluation of individual recommendations. Copyright © 2002-2012 The Design Society. All rights reserved.

Information models used to manage engineering change: A review of the literature 2005-2010

Engineering change is a significant part of any product development programme. Changes can arise at many points throughout the product life-cycle, resulting in rework which can ripple through different stages of the design process. Managing change processes is thus a critical aspect of any design project, especially in complex design. Through a literature review, this paper shows the diversity of information models used by different change management methods proposed in the literature. A classification framework for organising these change management approaches is presented. The review shows an increase in the number of cross-domain models proposed to help manage changes.