SegLink++: Detecting Dense and Arbitrary-shaped Scene Text by Instance-aware Component Grouping.

•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.