Scene Text Detection with Selected Anchor
This work addresses computational waste in scene text detection for applications requiring efficient real-time processing, though it is incremental as it builds on Faster RCNN.
The paper tackles the computational inefficiency of dense anchor schemes in scene text detection by proposing an anchor selection-based region proposal network (AS-RPN) that uses learnable, selected anchors to reduce anchor numbers while maintaining high recall. It achieves comparable performance to state-of-the-art methods on benchmarks like COCO-Text and ICDAR2015 using a single-scale ResNet50 model.
Object proposal technique with dense anchoring scheme for scene text detection were applied frequently to achieve high recall. It results in the significant improvement in accuracy but waste of computational searching, regression and classification. In this paper, we propose an anchor selection-based region proposal network (AS-RPN) using effective selected anchors instead of dense anchors to extract text proposals. The center, scales, aspect ratios and orientations of anchors are learnable instead of fixing, which leads to high recall and greatly reduced numbers of anchors. By replacing the anchor-based RPN in Faster RCNN, the AS-RPN-based Faster RCNN can achieve comparable performance with previous state-of-the-art text detecting approaches on standard benchmarks, including COCO-Text, ICDAR2013, ICDAR2015 and MSRA-TD500 when using single-scale and single model (ResNet50) testing only.