Detecting Oriented Text in Natural Images by Linking Segments

CVPR 2017 Baoguang ShiXiang BaiSerge Belongie

Most state-of-the-art text detection methods are specific to horizontal Latin text and are not fast enough for real-time applications. We introduce Segment Linking (SegLink), an oriented text detection method... (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 ICDAR 2013 SegLink F-Measure 85.3% # 10
Precision 87.7 # 12
Recall 83 # 11
Scene Text Detection ICDAR 2015 SegLink F-Measure 75 # 27
Precision 73.1 # 29
Recall 76.8 # 30
Scene Text Detection MSRA-TD500 SegLink Recall 70 # 9
Precision 86 # 6
F-Measure 77 # 6

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