Method to describe a screen capture using AI for the visually impaired

Abstract

Some disclosed embodiments are directed to methods and systems for performing accessible screen capturing that considers visually impaired users. For example, systems and methods are provided for selecting a screen capture type and determining a screen capture area. Systems temporarily apply the screen capture type to a user display according to the screen capture area and identify an object included in the screen capture area. Systems then obtain application metadata corresponding to the object and generate a screen capture description of the object based on the application metadata corresponding to the object. Subsequently, systems narrate the screen capture description of the object and then generate an image-based screen capture that comprises the object by applying the screen capture type according to the screen capture area and embedding the application metadata into the image-based screen capture.

Dependencies are inferred from the claim text.