Chrome can transform images into text for PDFs.
Google is developing built-in features in the Chrome browser, utilizing artificial intelligence (AI), to enhance the accessibility of PDFs for individuals who are blind or have low vision and rely on screen readers. One of the features being added to the Chrome browser on ChromeOS is the ability to convert images to text within PDFs.
When a screen reader encounters a PDF without alt text (a description of the image that can be read by screen readers), the screen reader will be able to convert the image to text and read it aloud. Google is expanding it’s existing ‘get image descriptions’ feature and introducing additional functionality for PDFs. Image descriptions are currently available in multiple languages.
Additionally, Google is introducing a ‘reading mode’ tool to the Chrome browser, which enables easier reading for students by adjusting text size, font, and removing distractions. The reading mode and images-to-text features will be gradually rolled out in the coming months.