CoVision

Rapid tests remain an important protective tool – but many visually impaired and blind people cannot read the test results themselves and are dependent on outside help. This compromises privacy, is inconvenient, and can prevent regular use. Thanks to improved accessibility on smartphones (e.g., VoiceOver) and modern computer vision techniques, this can be changed: photos of the test are automatically evaluated and the result is output acoustically or via a screen reader. MI4People is developing an easy-to-use, privacy-friendly solution for this very purpose, which increases independence and safety for visually impaired users.

Motivated by the original idea of Dr. Stefanie Lämmle from the InnovationLab of the City of Munich and discussions with Steffen Erzgraber from the Bavarian Association for the Blind and Visually Impaired, a group of students created a first working prototype of this application called CoVision. The team, consisting of Simon Farshid, Raphael Feigl, Brigitta Jesica Kartono, and Lennart Maack, created the prototype within 48 hours during the TUM.ai Makeathon and won first prize at the event!

The current prototype shows that such an application is feasible, but needs to be improved in terms of both accuracy and user-friendliness in order to offer blind people the greatest possible benefit. Such improvements require both additional resources and time for research.

Expected impact

This system will enable blind and visually impaired people to perform rapid antigen COVID tests themselves. It will increase comfort and privacy for this group of people and make testing more accessible. Overall, the app is expected to help protect the health of blind and visually impaired people and better integrate them into measures against the pandemic.