FER4HM is a joint research project between the STARS Team of the French Institute for Research in Computer Science and Automation (INRIA) and the Institute of Computing Technology (ICT) of the Chinese Academy of Sciences (CAS). FER4HM is a 3-year project, starting in Fall 2017
FER4HM aims to investigate computer vision methods for facial expression recognition in patients with Alzheimer’s disease. Most importantly though, the project seeks to be part of a paradigm shift in current healthcare, efficiently and cost-effectively finding objective measures to (a) assess different therapy treatments, as well to (b) enable automated human-computer interaction in remote scale healthcare-frameworks.
Recognizing expressions in severely demented Alzheimer’s disease (AD) patients is essential since such patients have lost a substantial amount of their cognitive capacity, and some even their verbal communication ability (e.g., aphasia). This leaves patients dependent on clinical staff to assess their verbal and non-verbal language, in order to communicate important messages, as of discomfort associated with potential complications of the AD. Such assessment classically requires the patients’ presence in a clinic, and time-consuming examination involving medical personnel. Thus, expression monitoring is costly and logistically inconvenient for patients and clinical staff, which hinders among others large-scale monitoring.
Approaches need to cater to the challenging settings of current medical recordings, which include continuous pose variations, occlusions, camera-movements, camera-artefacts, as well as changing illumination. Additionally and importantly, the (elderly) patients exhibit generally less profound facial activities and expressions in a range of intensities and predominantly occurring in combinations (e.g., talking and smiling).