Decomposition-Based Domain Adaptation for Real-World Font Recognition

TL;DR

This paper introduces DeepFont, a domain adaptation framework using a decomposition approach and auto-encoders to improve font recognition accuracy from synthetic to real-world images.

Contribution

It presents a novel domain adaptation method combining CNN decomposition and auto-encoders for fine-grain font recognition.

Findings

Achieved over 80% top-5 accuracy on real-world font dataset.

Effectively leverages unlabeled real images with synthetic data.

Outperforms previous font recognition methods.

Abstract

We present a domain adaption framework to address a domain mismatch between synthetic training and real-world testing data. We demonstrate our method on 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 font recognition methods (Chen et al. (2014)). In this paper, we introduce a Convolutional Neural Network decomposition approach, leveraging a large training corpus of synthetic data to obtain effective features for classification. This is done using an adaptation technique based on a Stacked Convolutional Auto-Encoder that exploits a large collection of unlabeled real-world text images combined with synthetic data preprocessed in a specific way. The proposed DeepFont method achieves an accuracy of higher than 80% (top-5) on a new large labeled real-world dataset we collected.