In this paper, we describe a Human Centered Multimedia Computing (HCMC) approach to the design and development of assistive and rehabilitative environments for people with disabilities. Unlike Human Computer Interaction (HCI), which was targeted at improving the usability of computing devices, HCMC addresses a higher level of functionality where machines adapt to the users resulting in elegant interactions. At the Center for Cognitive Ubiquitous Computing (CUbiC), we are engaged in a project for individuals who are blind and visually impaired, called iCARE (information technology Centric Assistive and Rehabilitative Environment). An overview of the iCARE project components is first presented followed by a detailed discussion of one example of our research effort, namely pose angle estimation of faces towards enhancing social interactions. © 2008 IEEE.