In a bid to curtail offensive memes that promote hate speech, Facebook is Constructing a Publication artificial intelligence (AI) system that uses machine Learning How to identify text in Pictures and videos in Addition to transcribe it.
While tools to transcribe text are nothing new, the organization faces different challenges because of the dimensions, sheer quantity of photographs shared each day on Facebook and Instagram, and the number of languages supported on its worldwide platform.
Together with the publication AI system named Rosetta, Facebook can process over a billion people images and Instagram images and video frames (in a wide variety of languages) per day through the system economically.
The extracted text is subsequently used by downstream classifiers to instantly act upon policy-violating content or by product programs like photo search.
“Understanding text in pictures alongside the context where it seems helps our methods to identify inappropriate or harmful content and keep our community safe,” the social networking giant said in a blog post late on Tuesday.
“Text extracted from images is used to improve the value and quality of photo search, automatically identifying articles that violates our hate-speech policy on the stage in various languages, and enhance the validity of classification of photos in News Feed to surface personalised content,” the media giant noted.
Further, Facebook is also continuing to invest in expanding the text recognition version for the broad selection of languages used on its own worldwide platform.