Facebook is soon going to introduce a new AI tool that would let users replicate a font or handwriting just by taking a picture. Facebook on Monday announced a new AI Tool called TextStyleBrush, that copies the font of a handwritten text or a text at an image just by looking at one example word. The new tool can mimic various fonts and different writing styles.
"Today, we're introducing TextStyleBrush, the first self-supervised AI model that replaces text in existing images of both scenes and handwriting in one shot using just a single example word. The work will also be submitted to a peer-reviewed journal.It works similar to the way style brush tools work in word processors, but for text aesthetics in images. It surpasses state-of-the-art accuracy in both automated tests and user studies for any type of text. Unlike previous approaches, which define specific parameters such as typeface or target style supervision, we take a more holistic training approach and disentangle the content of a text image from all aspects of its appearance of the entire word box," Facebook said in a blogpost.
Facebook claims that its AI tool is more flexible than other AI systems available as it is flexible enough to understand the nuances of both texts in real-world scenes and handwriting. The AI system that is used by Facebook recognises unlimited texts inducing rotating texts, curved texts, deformations that happen between paper and pen when handwriting, image noise and more. Facebook also said that some of the texts that its system faces difficulty in recognising metallic or multi-colour text.
Facebook said that this is a research project, but it could one day open doors to creative self-expression like personalized messaging and captions.
"Although this is a research project, it could one day unlock new potential for creative self-expression like personalized messaging and captions, and lays the groundwork for future innovations like a photo-realistic translation of languages in augmented reality (AR). By publishing the capabilities, methods, and results of this research, we hope to spur dialogue and research into detecting potential misuse of this type of technology, such as deepfake text attacks a critical, emerging challenge in the AI field," the blog read.
Copyright©2021 Living Media India Limited. For reprint rights: Syndications Today