Accessible PDFs for All

People with visual impairments use assistive technology, e.g., screen readers, to navigate and read PDFs. However, screen readers do not work correctly with native PDFs. They require PDF UA to enable all features. Most scientific PDFs do not fulfill the PDF UA norm. This presents a major barrier for screen readers users, wishing to pursue studies or careers in STEM fields.

Creating a PDF UA (PDF remediation) requires manual work, which is time-consuming and requires awareness and expert knowledge. We explore how we can use Artificial Intelligence to simplify the remediation process. Our research aims to lower barriers to creating accessible scientific PDFs, by reducing the time, effort, and expertise necessary to do so, ultimately facilitating greater access to scientific documents for people with visual impairments.

If you are interested to doing an independent study or your master's/bachelor's thesis on this topic, please contact

fschmitt@ifi.uzh.ch

• Felix Schmitt-Koopmann
• Prof. Elaine M. Huang
• Prof. Alireza Darvishy