Registration of eye reflection and scene images using an aspherical eye model.

This paper introduces an image registration algorithm between an eye reflection and a scene image. Although there are currently a large number of image registration algorithms, this task remains difficult due to nonlinear distortions at the eye surface and large amounts of noise, such as iris texture, eyelids, eyelashes, and their shadows. To overcome this issue, we developed an image registration method combining an aspherical eye model that simulates nonlinear distortions considering eye geometry and a two-step iterative registration strategy that obtains dense correspondence of the feature points to achieve accurate image registrations for the entire image region. We obtained a database of eye reflection and scene images featuring four subjects in indoor and outdoor scenes and compared the registration performance with different asphericity conditions. Results showed that the proposed approach can perform accurate registration with an average accuracy of 1.05 deg by using the aspherical cornea model. This work is relevant for eye image analysis in general, enabling novel applications and scenarios.

Engagement and experience of older people with socially assistive robots in home care.

Social isolation is one of the most common consequences of older people with dementia, especially for those who live at their own dwellings alone due to limited access to social activities. Research relating to the use of social robots in aged care has increasing attention to facilitating the support to care services for older people with dementia. Particularly less attention has focused on the applicability of social robots in home care services. This paper aims to study the engagement and robot experience of older people with dementia while interacting with a social robot named Betty in the context of home-based care. This paper contributes to the research relating to care service embedded robots by expanding the knowledge regarding longitudinal research in home based care, while there is limited long-term study in this context. The results show that social robots are evident to be able to engage with older people with dementia at home. Consequently, designing social robots in a social context is desirable. While the robots enabled service for the human partner within the social context is possible, there is a need to underpin the concept of personhood to realize personalization of services and its contents to suit individual preferences.