SegLink++: Detecting Dense and Arbitrary-shaped Scene Text by Instance-aware Component Grouping
作者：
Highlights：
• A novel bottom-up method for detecting dense and arbitrary-shaped scene texts.
• Explicitly learning repulsive links between close texts helps to separate dense text instances.
• Instance-aware loss for bottom-up deep learning-based methods, further boosting the performance.
• A dataset consisting of dense and arbitrary-shaped scene text of commodity images is introduced.
• Significantly improved performance on dense and curved text detection.
摘要
•A novel bottom-up method for detecting dense and arbitrary-shaped scene texts.•Explicitly learning repulsive links between close texts helps to separate dense text instances.•Instance-aware loss for bottom-up deep learning-based methods, further boosting the performance.•A dataset consisting of dense and arbitrary-shaped scene text of commodity images is introduced.•Significantly improved performance on dense and curved text detection.
论文关键词：Scene text detection,Multi-oriented text,Curve text,Dense text
论文评审过程：Received 1 April 2019, Revised 6 June 2019, Accepted 24 June 2019, Available online 25 June 2019, Version of Record 19 July 2019.
论文官网地址：https://doi.org/10.1016/j.patcog.2019.06.020
