Scene Text Detection with Selected Anchor
arXiv:2008.08523
Abstract
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.
8 pages
References in corpus (8)
- TextBoxes++: A Single-Shot Oriented Scene Text Detector
- R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detection
- TextBoxes: A Fast Text Detector with a Single Deep Neural Network
- COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images
- Scene Text Detection via Holistic, Multi-Channel Prediction
- EAST: An Efficient and Accurate Scene Text Detector
- Scene Text Detection and Recognition: The Deep Learning Era
- TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes