Real-World Font Recognition Using Deep Network and Domain Adaptation

ICLR 2015

Publication date: May 7, 2015

Zhangyang Wang, Jianchao Yang, Hailin Jin, Eli Shechtman, Aseem Agarwala, Jonathan Brandt, Thomas S. Huang

We address a challenging fine-grain classification problem: recognizing a font style from an image of text. In this task, it is very easy to generate lots of rendered font examples but very hard to obtain real-world labeled images. This real-to-synthetic domain gap caused poor generalization to new real data in previous methods (Chen et al. (2014)). In this paper, we refer to Convolutional Neural Networks, and use an adaptation technique based on a Stacked Convolutional Auto-Encoder that exploits unlabeled real-world images combined with synthetic data. The proposed method achieves an accuracy of higher than 80% (top-5) on a real-world dataset.

Learn More