Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

TextBoxes: A Fast Text Detector with a Single Deep Neural Network

About

This paper presents an end-to-end trainable fast scene text detector, named TextBoxes, which detects scene text with both high accuracy and efficiency in a single network forward pass, involving no post-process except for a standard non-maximum suppression. TextBoxes outperforms competing methods in terms of text localization accuracy and is much faster, taking only 0.09s per image in a fast implementation. Furthermore, combined with a text recognizer, TextBoxes significantly outperforms state-of-the-art approaches on word spotting and end-to-end text recognition tasks.

Minghui Liao, Baoguang Shi, Xiang Bai, Xinggang Wang, Wenyu Liu• 2016

Related benchmarks

TaskDatasetResultRank
Text DetectionTotal-Text
Recall45.5
139
Text DetectionTotal-Text (test)
F-Measure52.5
126
Scene Text DetectionTotalText (test)
Recall45.5
106
Scene Text SpottingTotal-Text (test)
F-measure (None)36.3
105
Text DetectionICDAR 2013 (test)
F1 Score86
88
Text LocalizationICDAR 2013 (test)
Recall83
28
End-to-End Text SpottingICDAR 2013 (test)
Score S93.9
25
End-to-end RecognitionTotal-Text
F1 Score36.3
22
End-to-End Text RecognitionTotal-Text (test)
F-measure (None)36.3
17
Word SpottingICDAR 2013
Generic Score87
12
Showing 10 of 15 rows

Other info

Follow for update