Robust face recognition with partial occlusion, illumination variation and limited training data by optimal feature selection

This study investigates face recognition with partial occlusion, illumination variation and their combination, assuming no prior information about the mismatch, and limited training data for each person. The authors extend their previous posterior union model (PUM) to give a new method capable of dealing with all these problems. PUM is an approach for selecting the optimal local image features for recognition to improve robustness to partial occlusion. The extension is in two stages. First, authors extend PUM from a probability-based formulation to a similarity-based formulation, so that it operates with as little as one single training sample to offer robustness to partial occlusion. Second, they extend this new formulation to make it robust to illumination variation, and to combined illumination variation and partial occlusion, by a novel combination of multicondition relighting and optimal feature selection. To evaluate the new methods, a number of databases with various simulated and realistic occlusion/illumination mismatches have been used. The results have demonstrated the improved robustness of the new methods.

Extension of general practice training from three to four years: experiences of a vocational training programme in Southern Ireland

The aim of this study was to evaluate the experiences of trainees taking part in an extended (four-year) general practice training programme introduced in the South Eastern region of the Republic of Ireland to replace the previous traditional (three-year) programme. In a qualitative design, eight homogeneous focus groups were held to determine the value of the additional year of training. The first cohort of trainees was interviewed towards the start and at the end of their fourth year. Trainees finishing the following year were also interviewed, as were graduates from the final three-year programme. GP trainers and the four members of the programme directing team comprised two further independent focus groups. Trainees reported that the integration of hospital posts and general practice attachments over the four years was particularly beneficial. The exposure to a variety of different general practices and the opportunity to take part in specialty clinics were considered extremely useful. The fourth year of training was felt to be less pressurised than previous years. Professional and personal development was enhanced; improved readiness to practise and confidence were noted. Perceived disadvantages of extended training included a lack of acknowledgment for doctors in their fourth year and excessive emphasis placed on research during the final year of training. The addition of an extra year of vocational training improves professional and personal development and changes the learning experience for doctors. Doctors felt more confident and ready to enter independent practice at the end of the fourth year of training.

Assessing and training standing balance in older adults: A novel approach using the 'Nintendo Wii' Balance Board

Older adults, deemed to be at a high risk of falling, are often unable to participate in dynamic exercises due to physical constraints and/or a fear of falling. Using the Nintendo 'Wii Balance Board' (WBB) (Nintendo, Kyoto, Japan), we have developed an interface that allows a user to accurately calculate a participant's centre of pressure (COP) and incorporate it into a virtual environment to create bespoke diagnostic or training programmes that exploit real-time visual feedback of current COP position. This platform allows researchers to design, control and validate tasks that both train and test balance function. This technology provides a safe, adaptable and low-cost balance training/testing solution for older adults, particularly those at high-risk of falling.