Improved localization accuracy by LocNet for Faster R-CNN based text detection in natural scene images
作者：
Highlights：
• We are motivated to address the text localization accuracy problem and propose replacing the bounding box regression module with a novel LocNet based localization module to improve the localization accuracy of a Faster R-CNN based text detector.
• We present a simple yet effective two-stage approach to convert the difficult multi-oriented text detection problem to a relatively easier horizontal text detection problem, which makes our approach able to robustly detect multi-oriented text instances with accurate bounding box localization.
• Experiments demonstrate that our proposed approach boosts the localization accuracy of Faster R-CNN based text detectors significantly.
• Our new text detector has achieved superior performance on both horizontal (ICDAR-2011, ICDAR-2013 and MULTILIGUL) and multi-oriented (MSRA-TD500, ICDAR-2015) text detection benchmark tasks.
摘要
•We are motivated to address the text localization accuracy problem and propose replacing the bounding box regression module with a novel LocNet based localization module to improve the localization accuracy of a Faster R-CNN based text detector.•We present a simple yet effective two-stage approach to convert the difficult multi-oriented text detection problem to a relatively easier horizontal text detection problem, which makes our approach able to robustly detect multi-oriented text instances with accurate bounding box localization.•Experiments demonstrate that our proposed approach boosts the localization accuracy of Faster R-CNN based text detectors significantly.•Our new text detector has achieved superior performance on both horizontal (ICDAR-2011, ICDAR-2013 and MULTILIGUL) and multi-oriented (MSRA-TD500, ICDAR-2015) text detection benchmark tasks.
论文关键词：Text detection,Text localization accuracy,Faster R-CNN,LocNet,Natural scene images
论文评审过程：Received 12 September 2017, Revised 28 March 2019, Accepted 31 July 2019, Available online 3 August 2019, Version of Record 7 August 2019.
论文官网地址：https://doi.org/10.1016/j.patcog.2019.106986
