AdobeVFR syn

Adobe Visual Font Recognition synthetic dataset

ImagesIntroduced 2015-07-12

Subset of AdobeVFR. The dataset contains images depicting English text and consists of 1000 synthetic images for training and 100 for testing, for each of 2383 font classes. The training and test sets are called VFR_syn_train and VFR_syn_val, respectively.

The other part of AdobeVFR consists of "real-world text images".

Benchmarks

Font Recognition/Top 1 Accuracy Font Recognition/Top 5 Accuracy Font Recognition/Top-1 Error Rate Font Recognition/Top 5 Error Rate