To support a global platform and the number of languages in the world, investment is being carried out by extending the text recognition model for the wide number of languages used on Facebook. We are therefore exploring ways to bridge the domain gap between our synthetic engine and real-world distribution of text on images. To handle the task, the company has now designed a very sophisticated artificial intelligence which is known as Rosetta.
Named Rosetta, the system is already live and is extracting text from nearly one billion images and video frames posted on Facebook and Instagram daily, according to the social media giant. It will scan all the image on which it is overlaid which will lead to the engineers I order to equip Rosetta with the predictive capabilities.
The authors spend a substantial amount of time in the original paper describing how they tuned the system for optimal speed for "inference", when a new photo is looked at and has to be quickly searched for text and transcribed. It will analyze the images as well as it will use the historical data which is rather than the visual profile of the individual characters to understand the writing. In other words, Facebook developed an AI that can tell if a meme is offensive. So while Rosetta isn't dedicated to memes, their prevalence on Facebook and Instagram will undoubtedly make them a major use case, especially in Facebook's detection of offensive material.
Facebook Inc (NASDAQ:FB)'s more than 2.2 billion users share a staggering number of images on the platform each day that the social giant needs to catalog, add to search results and scan for harmful content. The overall process involves two steps of detecting a rectangular region that might contain text and then performing text recognition using a convolutional neural network (CNN). It will be extended to more areas in the future. "The naive approach of applying image-based text extraction to every single video frame is not scalable, because of the massive growth of videos on the platform, and would only lead to wasted computational resources".