| 作者、单位 | 数据集 | backbone | ||||||
|---|---|---|---|---|---|---|---|---|
| A Novel Integrated Framework for Learning both Text Detection and Recognition |
阿里巴巴 2018 |
Chinese Business Card Database IAM Handwriting Database |
VGG-16 network | e2e | ADAM | |||
| Deep Matching Prior Network: Toward Tighter Multi-oriented Text Detection | ICDAR 2015 Competition | |||||||
| TextBoxes | ||||||||
| TextBoxes++ | ||||||||
| AE_TextSpotter | http://github.com/whai362/AE TextSpotter | |||||||
| Mask TextSpotter | ||||||||
| Mask TextSpotter v3 | Mask TextSpotter v3: Segmentation Proposal Network for Robust Scene Text Spotting |
https://github.com/MhLiao/MaskTextSpotterV3 |
||||||
| Single Shot TextSpotter | ||||||||
| TextSnake | TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes | |||||||
| SSD |
PASCAL VOC2007 |
https://github.com/weiliu89/caffe/tree/ssd | VGG16 | |||||
| EAST |
EAST: An Efficient and Accurate Scene Text Detector |
|||||||
| YOLO | ||||||||
| YOLOv2 | ||||||||
| YOLO9000 | ||||||||
| YOLOv5 | ||||||||
| Mask RCNN | ||||||||
| Faster R-CNN | ||||||||
| Fast RCNN | ||||||||
| MultiBox | ||||||||
| ESIR | ESIR: End-to-end Scene Text Recognition via Iterative Image Rectificatio | |||||||
| UNet | ||||||||
| SegLink | ||||||||
| SWT | ||||||||
| MSER | ||||||||
| PSENet | ||||||||