Topics

Welcome to the NVDA Community Add-ons website - Image Describer #feed


nvda-addons@nvda-addons.groups.io Integration <nvda-addons@...>
 

Image Describer

  • Author: Oliver Edholm
  • Download at http://www.screenreader.ai
  • stable version

This add-on gives descriptions of images for you by utilizing methods in Machine Learning.

Notes:

  • The shortcut to get an image description of the current navigator object is NVDA+Control+I.
  • If you configure another language than English, the description could have translation issues because it's automatically generated.
  • The language of the descriptions that are generated are linked with the configured NVDA language. In other words, if you have Swedish configured, you will get Swedish descriptions, unless you change the language in the Image describer settings.
  • You can change the shortcut in the Input gestures menu, under the Image describer category.

Security:

  • The images are sent to a script hosted on the Google Cloud Platform for analysis. After the analysis the image gets removed from the server and will never be seen again.

For developers:

  • If you want to fiddle with the add-on, first run the deps.py script.


Noelia Ruiz
 

Hi, the add-on is registered in the translation system. Now I see an error, but I think this is caused since documentation has not been translated for any language.

Thanks

El 17/03/2019 a las 21:07, nvda-addons@nvda-addons.groups.io Integration escribió:
Image Describer
<http://addons.nvda-project.org/addons/ImageDescriber.en.html>
* Author: Oliver Edholm
* Download at http://www.screenreader.ai
* stable version
<https://addons.nvda-project.org/files/get.php?file=imgdesc>
This add-on gives descriptions of images for you by utilizing methods in Machine Learning.
Notes:
* The shortcut to get an image description of the current navigator
object is NVDA+Control+I.
* If you configure another language than English, the description
could have translation issues because it's automatically generated.
* The language of the descriptions that are generated are linked with
the configured NVDA language. In other words, if you have Swedish
configured, you will get Swedish descriptions, unless you change the
language in the Image describer settings.
* You can change the shortcut in the Input gestures menu, under the
Image describer category.
Security:
* The images are sent to a script hosted on the Google Cloud Platform
for analysis. After the analysis the image gets removed from the
server and will never be seen again.
For developers:
* If you want to fiddle with the add-on, first run the deps.py script.


Oliver Edholm
 

Awesome, thanks for going through everything Noelia!