translate

Generate or retrieve text descriptions/tags for poorly labeled images

This area consists of two methods for labeling images:

  • Automatically analyzing images, their context, and their metadata in order to provide a thorough and accurate description that is accessible to someone who cannot see the image. This may take the form of a text description or tag.
  • Additionally, this area may draw from the image tagging protocols used by popular sites such as Flickr, Facebook, and Google, and would benefit greatly if these sites were to converge on a single, standard tagging protocol.

Discussion by Disabilities

Blindness

Text descriptions of images can greatly increase understanding of a site for those who cannot see

Low Vision

Text descriptions of images can greatly increase understanding of a site for those who have low vision

Cognitive, Language, Learning Disabilities & Low Literacy

Text descriptions of images can assist people with cognitive, language, and learning disabilities in understanding the image’s content

Existing Products

This listing includes a wide range of products, from screen readers, to simple text-to-speech utilities, to large literacy suites that include a text-to-speech application. Please note that these products are not necessarily endorsed by RtF, but represent the range of available options.

Free, not necessarily open source

These products are free to use, but may have strict restrictions on viewing and modifying source code.

Related Research and Papers