Abstract
Missing or low-quality alternative text, or alt text, frequently impedes web and document accessibility. Alt text includes descriptive information attached to an image that screen readers use to describe visual content to visually impaired users. A deficiency in alt text creates a barrier for users who depend on screen readers to interpret visual content on webpages. The disclosure describes a method whereby a web browser or document viewer utilizes a generative model to analyze the content of an image to be displayed. If the image is not associated with alternative text that describes the image adequately, the web browser or document viewer generates or modifies descriptive text about the image and dynamically inserts the descriptive text into an image alt text attribute. The image alt text attribute may include the alt text attribute within a Document Object Model, an accessibility tree, or a tag tree where the descriptive text remains accessible to a screen reader. Automated generation of alt text provides descriptive metadata for previously difficult to access visual content.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Azose, Benjamin Albert, "Automated Generation and Dynamic Insertion of Image Alternative Text via Generative Models", Technical Disclosure Commons, ()
https://www.tdcommons.org/dpubs_series/10070