Image description - Generate or retrieve text descriptions/tags for poorly labeled images
This area consists of two methods for labelling 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.
Related RtF projects and Discussion Groups
- Blindness and Low Vision Discussion Group (BLVDG)
- Cognitive Language and Learning Discussion Group (CLLDG)
Discussion by Disabilities (Benefits & Preferred Behaviors)
Blind
- 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
- 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.
- WebVisum - WebVisum
Related Research and Papers
- WebInSight:: making web images accessible - University of Washington - Bigham, J.P., Kaminsky, R.S., Ladner, R.E., Danielsson, O.M., and Hempton, G.L. (2006)
- Automated tactile graphics translation: in the field - University of Washington - Jayant, C., Renzelmann, M., Wen, D., Krisnandi, S., Ladner, R., and Comden, D. (2007)
- Accessible image file formats: the need and the way (position paper) - IBM - Patil, S.R. (2007)
- An adaptive & adaptable approach to enhance web graphics accessibility for visually impaired people - Queen's University Belfast - Tan, C.C., Yu, W., and McAllister, G. (2007)
- Improving accessibility of html documents bygenerating image-tags in a proxy - German Research Center for AI - Keysers, D., Renn, M., and Bruel, T.M. (2007)
- Increasing web accessibility by automatically judging alternative text quality - University of Washington - Bigham, J.P. (2007)
- Effective Practices for Description of Science Content within Digital Talking Books - NCAM - B. Gould, T. O'Connell, and G. Freed (2008)
Contributions & Discussion
Any corrections, suggestions, or additions to this page? Please let us know by emailing Contribution@RaisingTheFloor.org with [MasterList] in the subject line.
You can also join the discussion on the Access Feature Master List Google Group.



