Artificial intelligence that mimics handwriting opens a new era!
Scientists at the University of Abu Dhabi have successfully developed an artificial intelligence tool that can faithfully mimic human handwriting. This innovative tool, using a neural network-based vision transformer, has even been patented in the US. The work on the project, which has the potential to change the paradigm of writing, was led by a team of researchers from Mohamed Bin Zayed University of Artificial Intelligence.
Traditionally, handwriting was considered a unique personal style that allowed different people’s texts or signatures to be distinguished. Handwriting style was important for identifying the author and was used in the field of graphology to estimate the psychological profile of the writer. However, the new tool, with the analysis of mere paragraphs, can reproduce human handwriting and offers possibilities such as mimicking the writing style for people with disabilities.
The developers highlight the potential use for decoding illegible handwriting such as medical notes. However, due to potential misuse (e.g. forging signatures), the tool is not yet publicly available. The research team is trying to raise awareness and educate the public about the risks, while working on the security of the tool.
The developers tested the quality of the tool by comparing samples of its writing with human samples and unexpectedly found that participants preferred the artificial handwriting. The artificial intelligence is currently able to mimic handwriting in English and some French, with the challenge of writing in Arabic. However, researchers are looking to overcome this hurdle and expand the tool’s repertoire to other languages in the future.
Photo source: www.pexels.com
Author of this article
WAS THIS ARTICLE HELPFUL?
Support us to keep up the good work and to provide you even better content. Your donations will be used to help students get access to quality content for free and pay our contributors’ salaries, who work hard to create this website content! Thank you for all your support!
OR CONTINUE READING