Adobe Intern Develops Font Recognition System

Wang_ZhangyangDeepFont has been ECE Illinois grad student, Zhangyang “Atlas” Wang’s project since he worked an internship with Adobe Research in the summer of 2014. This new platform for Adobe products has the ability to scan pictures and determine the fonts of text inside them.

This software, described by Adobe principal scientist Hailin Jin at the company’s MAX conference as “Shazam for fonts,” is DeepFont. What’s more: this isn’t a hypothetical technology – it’s already been shipped with Adobe’s latest editions of Photoshop and Typekit and is already popular with the design and academic communities.

Before its release, a demo of the software was presented to an audience of design professionals at the MAX conference to roaring applause. Since then, DeepFont has amassed several endorsements from designers and firms around the world, just a few of which are visible on its rapidly expanding hashtag on Twitter.

Font recognition is a huge need for designers, who traditionally rely upon professionals who charge high rates and take an average of 45 minutes to an hour to reliably determine fonts.

“I’m happy to resolve a need that the design community has been feeling for so long,” Wang said. “There’s definitely a sense of accomplishment when people like what you’ve developed, that’s a great feeling.”

The software itself works using a new type of machine learning called deep learning, which aims to create algorithms that mimic the human brain by continuously learning, recognizing patterns, and improving their performance.

Wang and his team started by building a database of real-world images with text, and teaching their algorithm the basics of distinguishing fonts. They designed the algorithm to work from this training, feeding it new examples and allowing it to recognize patterns. It will continuously refine its recognition abilities.

“The chance to work with Adobe on DeepFont was incredible. It was definitely one of the best internship experiences I’ve had,” Wang said. “Besides the game-changing nature of what we were developing, the people at Adobe were always very friendly and passionate about their work. The teams were small and specialized enough that I could have regular lunch meetings with the development head of Photoshop. She could tell me exactly how she wanted DeepFont to look and feel, and I could implement her specifications the same day.”

Click here to view the complete article posted on ECE Illinois.