What do you believe is the single most important factor driving up the cost of living in Nigeria?

A world of color and texture could soon become more accessible to people who are blind or have low vision, via new software that narrates what a camera records.

The tool, called WorldScribe, was designed by University of Michigan researchers and will be presented at the 2024 ACM Symposium on User Interface Software and Technology in Pittsburgh.

The study is titled "WorldScribe: Towards Context-Aware Live Visual Descriptions" and appears on the arXiv preprint server.

The tool uses generative AI (GenAI) language models to interpret the camera images and produce text and audio descriptions in real time to help users become aware of their surroundings more quickly. It can adjust the level of detail based on the user's commands or the length of time that an object is in the camera frame, and the volume automatically adapts to noisy environments like crowded rooms, busy streets and loud music.

Credit: Ruei-Che Chang

• Read More