A map crated by IDEO allows designers to explore relations between fonts

Even for professional designers, choosing a font can be a daunting task. This is why it is common to stick with the tested few and rarely branch out to explore the uncharted font territory. In efforts to change this and to help visualize the vast array of available options, IDEO created the Font Map.

The project is a brainchild of Kevin Ho, Software Designer at IDEO who used machine learning to sort fonts by visual characteristics, allowing for easier and more intuitive exploration.

Leveraging the Google Fonts database, the interactive map displays 750 letters “A” written using different typefaces. After hovering over them, users can see the font’s name and sample “Lorem Ipsum,” and after clicking on any of them, they can see similar fonts in the sidebar.

The map is based primarily on two open-source algorithms. “I used a convolutional neural network called VGG16 to generate for each font a list of numbers that represents what the network thought were the notable visual features of the image,” Ho explained in a Medium post. “Finally, in order to get x,y points, I ran these embeddings through T-SNE, a popular algorithm for taking large vectors and compressing them into a smaller space — in this case into a 2-D plane.”

The algorithm generated clear clusters that correspond to the traditional division of typefaces, like serif, sans-serif and cursive. In addition, there is a cluster of outliers or fonts that had fewer relations with others.

Given that AI allows for great scalability, thousands of different fonts could be cataloged and displayed in this way. Ho also mentioned that he would be interested to “explore how popular pairings would show up on Font Map.”

IDEO

Even for professional designers, choosing a font can be a daunting task. This is why it is common to stick with the tested few and rarely branch out to explore the uncharted font territory. In efforts to change this and to help visualize the vast array of available options, IDEO created the Font Map.

The project is a brainchild of Kevin Ho, Software Designer at IDEO who used machine learning to sort fonts by visual characteristics, allowing for easier and more intuitive exploration.

Leveraging the Google Fonts database, the interactive map displays 750 letters “A” written using different typefaces. After hovering over them, users can see the font’s name and sample “Lorem Ipsum,” and after clicking on any of them, they can see similar fonts in the sidebar.