In a bid to curtail offensive memes that promote hate speech, Facebook is building a Publication artificial intelligence (AI) system that uses machine Learning How to identify text from images and videos in Addition to transcribe it.
While resources to transcribe text are nothing new, the organization faces different challenges because of the dimensions, sheer quantity of photos shared every day on Facebook and Instagram, and also the amount of languages supported on its global platform.
With the publication AI system called Rosetta, Facebook can process over a billion public pictures and Instagram pictures and video frames (at a wide variety of languages) per day through the system efficiently.
The extracted text is then utilized by downstream classifiers to instantly act upon policy-violating articles or from product applications like picture search.
“Recognizing text in images alongside the context where it seems helps our methods to identify improper or harmful content and keep our community safe,” the social networking giant said in a blog article late on Tuesday.
“Text extracted from images is being used to enhance the relevance and quality of photo search, automatically identifying content that violates our hate-speech policy on the platform in a variety of languages, and enhance the validity of classification of photos from News Feed to surface more personalised content,” the networking giant noted.
Further, Facebook is also continuing to invest in expanding the text recognition version for the broad number of languages used on its own worldwide platform.