Meryem Erbilek

Framework for managing ageing effects in signature biometrics

This paper investigates and explores the impact of physical ageing in signature biometrics. Experimental performance evaluation, using three different signature databases, is carried out to provide some new insights into the relationship between different practical factors, in particular clarifying the impact on recognition performance of the data collection protocols used and the use of the feature pools underpinning the signature processing. This analysis provides an alternative perspective from which to explore and manage physical ageing effects in signature biometrics. The paper demonstrates that the proposed strategy maximises system accuracy while minimising the performance differential across a population which is heterogeneous with respect to age, and across different databases. The results presented suggest that adoption of the strategy proposed can render a template update procedure less critical than hitherto expected.

Enhancing the forensic value of handwriting using emotion prediction

Handwriting biometrics have a long history, especially when the handwritten signature is the target, but it has also proved possible to use handwriting as a basis for the prediction of various non-unique but forensically useful characteristics of the writer. Most commonly, these are socalled “soft biometric” characteristics such as the age or gender of the writer, but the predictive capabilities arising in handwriting offer wider opportunities for trait prediction. This paper presents a preliminary study of the use of handwriting to predict information about the writer relating specifically to higher level characteristics such as emotional state. We present some initial results to demonstrate that this is possible, and explore a number of particular factors relevant to the use of such a capability in areas of forensic investigation.

Automatic Handwriting Feature Extraction, Analysis and Visualization in the Context of Digital Palaeography

Digital palaeography is an emerging research area which aims to introduce digital image processing techniques into palaeographic analysis for the purpose of providing objective quantitative measurements. This paper explores the use of a fully automated handwriting feature extraction, visualization, and analysis system for digital palaeography which bridges the gap between traditional and digital palaeography in terms of the deployment of feature extraction techniques and handwriting metrics. We propose the application of a set of features, more closely related to conventional palaeographic assesment metrics than those commonly adopted in automatic writer identification. These features are emprically tested on two datasets in order to assess their effectiveness for automatic writer identification and aid attribution of individual handwriting characteristics in historical manuscripts. Finally, we introduce tools to support visualization of the extracted features in a comparative way, showing how they can best be exploited in the implementation of a content-based image retrieval (CBIR) system for digital archiving.

Exploring Gender Prediction from Iris Biometrics

Prediction of gender characteristics from iris images has been investigated and some successful results have been reported in the literature, but without considering performance for different iris features and classifiers. This paper investigates for the first time an approach to gender prediction from iris images using different types of features (including a small number of very simple geometric features, texture features and a combination of geometric and texture features) and a more versatile and intelligent classifier structure. Our proposed approaches can achieve gender prediction accuracies of up to 90% in the BioSecure Database.

Study of automatic prediction of emotion from handwriting samples

Handwriting biometrics has a long history, especially when the handwritten signature is the target, but it has also proved possible to use handwriting as a basis for the prediction of various non-unique but forensically useful characteristics of the writer, generally considered to be examples of so-called ‘soft biometrics’. Most commonly, these are characteristics such as the age or gender of the writer, but the predictive capabilities arising in handwriting offer wider opportunities for trait prediction. This study presents a preliminary investigation of the use of handwriting to predict information about the writer relating specifically to higher level characteristics such as emotional state. The authors present an initial study to demonstrate that this is possible, and explore a number of factors particularly relevant to the use of such a capability in areas of forensic investigation.

Exploiting biometric measurements for prediction of emotional state: A preliminary study for healthcare applications using keystroke analysis

Biometric measurements are now often routinely adopted as a robust means of determining individual identity. Such an approach is clearly beneficial in a variety of scenarios, including those relating to medical environments. In the medical context, however, the use of biometric data can potentially offer other valuable opportunities for harnessing the power of biometrics which have a more direct bearing on healthcare monitoring and treatment delivery. In this paper we focus on the prediction of “soft” biometric data and, in particular, we describe an approach which aims to predict “higher level” characteristics about an individual, such as those which may broadly be described as emotional or mental state. We show how such a capability can be utilised in healthcare scenarios, and specifically, by presenting some initial analysis of results from newly acquired data in a keystroke-based data collection task, we identify the most crucial issues which must be addressed if our basic predictive technique is to be developed for practical viability.

TOWARDS THE DEVELOPMENT OF USER TOOLS FOR KNOWLEDGE ACQUISITION IN DIGITAL DOCUMENT ANALYSIS

Handwritten documents provide a rich source of data and, with the growth in the availability of digitised documents, it becomes increasingly important to improve our ability to analyse and extract “knowledge” from such sources. This paper describes an approach to the provision of tools which can extract information about the writer of handwritten documents, especially those which were written in earlier times and which constitute key elements in our heritage and culture. We show how the constraints inherent in such documents influence our analytical approach, and we also show how developing appropriate “knowledge extraction” techniques can also be essential in other, more general, important application scenarios.