Researchers from UCL, University College London have developed a computer software program called, ‘My Text in Your Handwriting,’ which uses a person’s handwriting sample, accurately replicating it.
Published in ACM Transactions on Graphics and funded by the EPSRC, the machine-learning algorithm is built around glyphs – which analyses handwriting, reproducing it in the style of the sample.
In a digital world dominated by the QWERTY keyboard, the new computer software could add a sense of personalization to writing.
How ‘My Text in Your Handwriting’ Works
The researchers asked a user to write on four A4-sized sheets of paper. This was then scanned and interpreted by a computer and human moderator, examining the position of letters and the style words were written in.
The program analyses and replicates the writer’s style, joining-up between letter, vertical and horizontal spacing and also the pen-line texture and color
The team then asked a group to decide if any envelopes (which were written by the computer software) were created by a computer. In 40 percent of cases, they were incorrect.
Handwriting Software and Multiple Uses
There are many apps that interpret handwriting and reproduce handwritten text, but none copy an individual’s handwriting with words that the user did not show the computer.
Tom Haines, from UCL said, “Our software has lots of valuable applications.”
“Stroke victims, for example, may be able to formulate letters without the concern of illegibility.”
Personalized messages could be another positive usage: “someone sending flowers as a gift could include a handwritten note without even going into the florist.”
“It could also be used in comic books where a piece of handwritten text can be translated into different languages without losing the author’s original style,” he said.
The software could also help in detecting forged documents, improving identity theft and online security.
With all the positive benefits, some could also use this computer software to forge signatures and handwriting for criminal and personal gain.
Direct Applications and Relevance
The scientists have analyzed and replicated handwriting of famous figures such as: Abraham Lincoln, Frida Kahlo and Arthur Conan Doyle.
Co-author, Dr Oisin Mac Aodha, said: “Up until now, the only way to produce computer-generated text that resembles a specific person’s handwriting would be to use a relevant font.”
“The problem with such fonts is that it is often clear that the text has not been penned by hand, which loses the character and personal touch of a handwritten piece of text.”
“What we’ve developed removes this problem and so could be used in a wide variety of commercial and personal circumstances.”
Take Aways
- Researchers from UCL, have developed a computer software program which uses a person’s handwriting sample, accurately replicating it.
- Personalised messages could help: stroke victims, comic books, retailers and improve fraud detection.
- The negative side: the replication of handwriting could advance online fraud.
