AdaptiFont was recently presented at CHI, the leading conference on Human Factors in Computing.
Language is undoubtedly the most widespread medium for the exchange of knowledge between humans. However, the spoken language or abstract text must be made visible to be read, whether on paper or on screen.
How does the appearance of a text affect its readability, that is, the way it is read, processed and understood? A team from the Center for Cognitive Science at TU Darmstadt investigated this question at the intersection of perceptual science, cognitive science and linguistics. Electronic text is even more complex. Texts are read on different devices under different external conditions. And although any digital text is formatted initially, users can resize it on the screen, change the brightness and contrast of the screen, or even select a different font when reading text on the web.
The TU Darmstadt research team has now developed a system that leaves the design of fonts to the user’s visual system. First, they had to find a way to synthesize new fonts. This was achieved using a machine learning algorithm, which learned the structure of fonts by analyzing 25 popular and classic fonts. The system is capable of creating an infinite number of new fonts that are any intermediate form of others – for example, visually halfway between Helvetica and Times New Roman.
Because some fonts can make text more difficult to read, they can slow down the reader. Other fonts can help the user to read more fluently. By measuring reading speed, a second algorithm can now generate more fonts that increase reading speed.
In a lab experiment, in which users read texts for an hour, the research team showed that their algorithm indeed generates new fonts that increase the reading speed of the individual user. Interestingly, all of the readers had their own custom font which made reading especially easy for them. However: this individual preferred typeface may not be suitable for all situations. “AdaptiFont can therefore be understood as a system that creates fonts for an individual dynamically and continuously while reading, which maximizes reading speed at the time of use. It may depend on the content of the text, whether you are tired or maybe using different display devices, ”explains Professor Constantin A. Rothkopf, Center for Cognitive Sciences and Director of the Institute of Information Processing Psychology at TU Darmstadt.
The AdaptiFont system was recently presented to the scientific community at the Conference on Human Factors in Computing Systems (CHI). A patent application has been filed. Possible future applications relate to all electronic devices on which the text is read.
Source of the story:
Material provided by Darmstadt University of Technology. Note: Content can be changed for style and length.