Paper Info
Title
DeepFont: Identify Your Font from An Image
Abstract
As font is one of the core design concepts, automatic font identification and similar font suggestion from an image or photo has been on the wish list of many designers. We study the Visual Font Recognition (VFR) problem [4] LFE, and advance the state-of-the-art remarkably by developing the DeepFont system. First of all, we build up the first available large-scale VFR dataset, named AdobeVFR, consisting of both labeled synthetic data and partially labeled real-world data. Next, to combat the domain mismatch between available training and testing data, we introduce a Convolutional Neural Network (CNN) decomposition approach, using a domain adaptation technique based on a Stacked Convolutional Auto-Encoder (SCAE) that exploits a large corpus of unlabeled real-world text images combined with synthetic data preprocessed in a specific way. Moreover, we study a novel learning-based model compression approach, in order to reduce the DeepFont model size without sacrificing its performance. The DeepFont system achieves an accuracy of higher than 80% (top-5) on our collected dataset, and also produces a good font similarity measure for font selection and suggestion. We also achieve around 6 times compression of the model without any visible loss of recognition accuracy.
Year
DOI
Venue
2015
10.1145/2733373.2806219
ACM Multimedia
Keywords
Field
DocType
Visual Font Recognition,Deep Learning,Domain Adaptation,Model Compression
Computer vision,Pattern recognition,Similarity measure,Computer science,Convolutional neural network,CUDA,Font,Synthetic data,Artificial intelligence,Test data,Deep learning,Artificial neural network
Journal
Volume
Citations 
PageRank 
abs/1507.03196
27
1.38
References 
Authors
17
7
Name
Order
Citations
PageRank
Zhangyang Wang143775.27
jianchao yang27508282.48
Hailin Jin31937108.60
Eli Shechtman44340177.94
Aseem Agarwala53125178.39
Jonathan Brandt689243.20
Thomas S. Huang7278152618.42