Papers › DeepFont: Identify Your Font from An Image

DeepFont: Identify Your Font from An Image

12 Jul 2015arXiv:1507.03196archive 2025-07-28

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

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, 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.

PaperPDFCode

Code

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Domain AdaptationFont RecognitionModel Compression

Datasets

Introduced by this paper, per the archive.

AdobeVFR realAdobeVFR syn

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Font Recognition AdobeVFR real DeepFont (CAE_FR) Top 1 Accuracy 71.42 #1 of 2 Archive leaderboard report
Font Recognition AdobeVFR real DeepFont (CAE_FR) Top 5 Accuracy 81.79 #1 of 2 Archive leaderboard report
Font Recognition AdobeVFR real DeepFont (CAE_FR) Top 5 Error Rate 18.21 #1 of 2 Archive leaderboard report
Font Recognition AdobeVFR real DeepFont (CAE_FR) Top-1 Error Rate 28.58 #1 of 2 Archive leaderboard report
Font Recognition AdobeVFR syn DeepFont (S) Top 1 Accuracy 98.97 #1 of 5 Archive leaderboard report
Font Recognition AdobeVFR syn DeepFont (S) Top 5 Accuracy 100 #1 of 5 Archive leaderboard report
Font Recognition AdobeVFR syn DeepFont (S) Top 5 Error Rate 0 #1 of 5 Archive leaderboard report
Font Recognition AdobeVFR syn DeepFont (S) Top-1 Error Rate 1.03 #1 of 5 Archive leaderboard report
Font Recognition AdobeVFR syn DeepFont (CAE_FR) Top 1 Accuracy 93.42 #3 of 5 Archive leaderboard report
Font Recognition AdobeVFR syn DeepFont (CAE_FR) Top 5 Accuracy 100 #3 of 5 Archive leaderboard report
Font Recognition AdobeVFR syn DeepFont (CAE_FR) Top 5 Error Rate 0 #3 of 5 Archive leaderboard report
Font Recognition AdobeVFR syn DeepFont (CAE_FR) Top-1 Error Rate 6.58 #3 of 5 Archive leaderboard report
Font Recognition AdobeVFR syn DeepFont (F) Top 1 Accuracy 92.6 #4 of 5 Archive leaderboard report
Font Recognition AdobeVFR syn DeepFont (F) Top 5 Accuracy 100 #4 of 5 Archive leaderboard report
Font Recognition AdobeVFR syn DeepFont (F) Top 5 Error Rate 0 #4 of 5 Archive leaderboard report
Font Recognition AdobeVFR syn DeepFont (F) Top-1 Error Rate 7.4 #4 of 5 Archive leaderboard report
Font Recognition VFR-Wild DeepFont (CAE_FR) Top 1 Accuracy 61.85 #1 of 2 Archive leaderboard report
Font Recognition VFR-Wild DeepFont (CAE_FR) Top 5 Accuracy 79.38 #1 of 2 Archive leaderboard report
Font Recognition VFR-Wild DeepFont (CAE_FR) Top 5 Error Rate 20.62 #1 of 2 Archive leaderboard report
Font Recognition VFR-Wild DeepFont (CAE_FR) Top-1 Error Rate 38.15 #1 of 2 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections