A team of scientists at Stanford University are using Google Glass that could recognize emotions, to help treat autism in children. The team is specifically using the platform to help them recognize and classify emotions they feel and see around them.
The Autism Glass Project uses machine learning for feature extraction, allowing the device to detect what the team refers to as "action units" from faces.
The second phase of the project is to conduct a study involving 100 children. The goal is to develop a platform that allows for easy at-home autism treatment. Google has even donated 35 more Glass devices to the project.
The Autism Project is led by Catalin Voss along with Dennis Wall, a professor in Stanford's school of medicine, and Nick Haber, a Stanford post-doc.
Voss said, "The Autism Project as an interactive learning experience. The children can be told by the app to look for someone who is happy. If they successfully point their head towards a happy face, they are awarded points. A child's use of the device is also recorded, allowing doctors and parents to go back and analyze performance and behaviors."
The team monitors the game performance of each participant in the study. The analysis will be combined with a video analysis and parental questionnaires to build a 'quantitative phenotype' of autism.
The researchers hope that tracking this over time, they will be able to show how their device helps improve emotion recognition over the long-term.
Voss hopes that the project will allow autism to be diagnosed early. Currently, the average age of diagnosis in the United States is four and a half years. Voss hopes to bring that to two and a half years.