The technology holds promise for generating synthetic data to enhance other AI models’ handwriting processing capabilities. While the current model can write in English and, to some extent, French.
Researchers at Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) in Abu Dhabi have unveiled a cutting edge technology capable of mimicking a person’s handwriting style with just a few paragraphs of written material. The system, developed using a transformer model neural network, has earned a patent from the US Patent and Trademark Office.
Although not yet publicly released, this development marks a significant advancement in an area long of interest to academics. While previous apps and robots could generate handwriting, recent AI progress has greatly enhanced character recognition techniques.
The potential applications are broad, from aiding the disabled to forging signatures, raising concerns about misuse. MBZUAI researchers emphasise the need for public awareness and anti-forgery tools.
Despite these concerns, they plan to deploy the technology for real-world use soon and seek commercial partnerships. According to Hisham Cholakkal and Rao Muhammad Anwer, both assistant professors at MBZUAI, applications range from deciphering doctors’ handwriting to tailored advertising.
“We’ll have to create public awareness and develop tools to combat forgery,” said Hisham Cholakkal, an assistant professor for computer vision at MBZUAI. “It’s like developing an anti-virus for a virus.”
“From decoding doctors’ handwriting to crafting personalised advertising, the potential of this development is huge,” said Rao Muhammad Anwer, also an assistant professor of computer vision at MBZUAI
The technology also holds promise for generating synthetic data to enhance other AI models’ handwriting processing capabilities. While the current model can write in English and, to some extent, French, efforts are ongoing to adapt it to Arabic handwriting.
As the technology continues to evolve, it is expected to revolutionise various industries and significantly impact how handwritten documents are produced and authenticated. With its potential to streamline processes and improve accessibility, the handwriting mimicking AI represents a significant step forward in the field of artificial intelligence.
