What problem does the project solve?
People who are visually impaired are facing challenges when they learn from written content. They are using software solutions based on text-to-speech engines, but when it comes to visual content like images, diagrams, or tables, those solutions are usually not descriptive enough, thus not helpful for the users. In the worst case, blind and visually impaired people are excluded from much content, knowledge and education.
How does your project address the problem?
The idea seeks to provide human generated descriptions of images and other visual content. The project wants to test a community-driven approach by involving volunteers for creating the description. Ideally, the solution could be connected and tested on structured data in Wikimedia Commons.