TextFuseNet: Scene Text Detection with Richer Fused Features

17 May 2020 Jian Ye Zhe Chen Juhua Liu Bo Du

Arbitrary shape text detection in natural scenes is an extremely challenging task. Unlike existing text detection approaches that only perceive texts based on limited feature representations, we propose a novel framework, namely TextFuseNet, to exploit the use of richer features fused for text detection... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK BENCHMARK
Scene Text Detection IC19-Art TextFuseNet (ResNet-101) H-Mean 78.6 # 1
Scene Text Detection ICDAR 2013 TextFuseNet (ResNet-101) F-Measure 94.61% # 1
Precision 97.27 # 2
Recall 92.09 # 2
Scene Text Detection ICDAR 2015 TextFuseNet (ResNet-101) F-Measure 92.23 # 1
Precision 93.96 # 1
Recall 90.56 # 2
Scene Text Detection SCUT-CTW1500 TextFuseNet (ResNet-101) F-Measure 87.4 # 1
Precision 89.7 # 1
Recall 85.1 # 2
Scene Text Detection Total-Text TextFuseNet (ResNet-101) F-Measure 87.5% # 1
Precision 89.2 # 3
Recall 85.8 # 1

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