Robust 2D Ear Registration and Recognition Based on SIFT Point Matching

Significant recent progress has shown ear recognition to be a viable biometric. Good recognition rates have been demonstrated under controlled conditions, using manual registration or with specialised equipment. This paper describes a new technique which improves the robustness of ear registration and recognition, addressing issues of pose variation, background clutter and occlusion. By treating the ear as a planar surface and creating a homography transform using SIFT feature matches, ears can be registered accurately. The feature matches reduce the gallery size and enable a precise ranking using a simple 2D distance algorithm. When applied to the XM2VTS database it gives results comparable to PCA with manual registration. Further analysis on more challenging datasets demonstrates the technique to be robust to background clutter, viewing angles up to +/- 13 degrees and with over 20% occlusion.

Incidence trends for childhood type 1 diabetes in Europe during 1989-2003 and predicted new cases 2005-20: a multicentre prospective registration study

Background: The incidence of type 1 diabetes in children younger than 15 years is increasing. Prediction of future incidence of this disease will enable adequate fund allocation for delivery of care to be planned. We aimed to establish 15-year incidence trends for childhood type 1 diabetes in European centres, and thereby predict the future burden of childhood diabetes in Europe.
Methods: 20 population-based EURODIAB registers in 17 countries registered 29 311 new cases of type 1 diabetes, diagnosed in children before their 15th birthday during a 15-year period, 1989–2003. Age-specific log linear rates of increase were estimated in five geographical regions, and used in conjunction with published incidence rates and population projections to predict numbers of new cases throughout Europe in 2005, 2010, 2015, and 2020.
Findings: Ascertainment was better than 90% in most registers. All but two registers showed significant yearly increases in incidence, ranging from 0·6% to 9·3%. The overall annual increase was 3·9% (95% CI 3·6–4·2), and the increases in the age groups 0–4 years, 5–9 years, and 10–14 years were 5·4% (4·8–6·1), 4·3% (3·8–4·8), and 2·9% (2·5–3·3), respectively. The number of new cases in Europe in 2005, is estimated as 15 000, divided between the 0–4 year, 5–9 year, and 10–14 year age-groups in the ratio 24%, 35%, and 41%, respectively. In 2020, the predicted number of new cases is 24 000, with a doubling in numbers in children younger than 5 years and a more even distribution across age-groups than at present (29%, 37%, and 34%, respectively). Prevalence under age 15 years is predicted to rise from 94 000 in 2005, to 160 000 in 2020.
Interpretation: If present trends continue, doubling of new cases of type 1 diabetes in European children younger than 5 years is predicted between 2005 and 2020, and prevalent cases younger than 15 years will rise by 70%. Adequate health-care resources to meet these children’s needs should be made available.