EAST: An Efficient and Accurate Scene Text Detector

Previous approaches for scene text detection have already achieved promising performances across various benchmarks. However, they usually fall short when dealing with challenging scenarios, even when equipped with deep neural network models, because the overall performance is determined by the interplay of multiple stages and components in the pipelines... (read more)

PDF Abstract CVPR 2017 PDF CVPR 2017 Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Scene Text Detection COCO-Text EAST + VGG16 F-Measure 39.45 # 3
Precision 50.39 # 3
Recall 32.4 # 3
Scene Text Detection ICDAR 2015 EAST + PVANET2x RBOX (single-scale) F-Measure 78.2 # 29
Precision 83.6 # 28
Recall 73.5 # 31
Scene Text Detection ICDAR 2015 EAST + PVANET2x RBOX (multi-scale) F-Measure 80.7 # 28
Precision 83.3 # 29
Recall 78.3 # 28
Scene Text Detection MSRA-TD500 EAST + PVANET2x Recall 67.43 # 10
Precision 87.28 # 5
F-Measure 76.08 # 7
Scene Text Detection Total-Text EAST F-Measure 42.0% # 15
Precision 50.0 # 12
Recall 36.2 # 12

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet