WordSup: Exploiting Word Annotations for Character based Text Detection
Open paper
Benchmark
Model
Rank
Results
scene-text-detection-on-icdar-2013
WordSup (VGG16-synth-icdar)
–
F-Measure: 90.34%
Precision: 93.34
Recall: 87.53
scene-text-detection-on-icdar-2015
SSTD
–
F-Measure: 77
Precision: 80
Recall: 73
Rank counts only results with a code link.