Calligrapher.ai is using AI for handwriting generation

In context: Researchers are turning the artistic world the wrong way up, exploiting synthetic intelligence and machine studying algorithms to show many duties into semi-autonomous processes. Nothing is protected from generative AI anymore, not even your native physician’s illegible writing.

Years earlier than OpenAI and different organizations began toying with AI to simply generate textual content, speech, artworks, malware, and movies, machine studying researcher Sean Vasquez was finding out a 2013 paper by Google DeepMind’s Alex Graves to create “handwriting synthesis” experiments.

Vasquez archived his code on GitHub alongside along with his web-based demo. The experiment is accessible at Calligrapher.ai, which Hacker Information just lately rediscovered. The handwriting synthesis behind Calligrapher.ai employs a generative technique constructed upon a recurrent neural community (RNN).

An RNN is a category of synthetic neural networks the place connections between nodes can create a cycle permitting output from some nodes to have an effect on subsequent enter to the identical nodes. Recurrent neural networks can exhibit temporal dynamic habits, which makes them significantly helpful in duties reminiscent of handwriting or speech recognition. Like another neural community, Vasquez skilled Calligrapher.ai on a reasonably massive dataset of calligraphy samples, primarily the IAM On-Line Handwriting Database.

The IAM-On database accommodates “types of handwritten English textual content acquired on a whiteboard,” with samples from 221 totally different “writers” and greater than 1,700 acquired varieties. The database contains 13,049 remoted and labeled textual content traces in “on-line” and “off-line” format, for a complete of 86,272 samples from an 11,059-word dictionary.

Calligrapher.ai can generate variable handwriting in 9 totally different kinds, whereas customers can change velocity, legibility, and stroke width sliders for additional customization. In contrast to conventional font varieties designed to imitate handwriting, each pattern generated by Calligrapher.ai must be distinctive even when the writing type is identical. Customers can obtain the ultimate outcome as an SVG vector file.

In accordance with Vasquez, the legibility slider employs a way often known as “adjusting the temperature of the sampling distribution” to change variation in handwriting. Outputs come from a “chance distribution,” and rising the legibility “successfully concentrates chance density round extra seemingly outcomes.”

Being only a demo, Calligrapher.ai is proscribed in scope regardless of its capacity to create plausible handwriting patterns. Moreover, Vasquez solely skilled the underlying RNN on English language samples, so the web site is not significantly good at reproducing accents generally utilized in different languages.