Abstract | ||
---|---|---|
•We propose a novel quadrilateral regression algorithm for generating quadrilateral proposals and text detections.•We introduce a dual-branch structure of a quadrilateral detection head and an additional rotated rectangle detection head to train the detection head at the second stage.•We design a novel weighted RoI pooling module with learned weight masks to pool the feature.•We propose an accelerated NMS algorithm for quadrilateral text proposals and detections.•We integrate the above four novel modules into the two-stage architecture of Faster R-CNN, and achieve state-of-the-art results on multiple public datasets. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1016/j.patcog.2020.107230 | Pattern Recognition |
Keywords | Field | DocType |
Scene text detection,Deep learning,Quadrilateral regression | Pattern recognition,Regression algorithm,Pooling,Rectangle,Region proposal,Network architecture,Quadrilateral,Artificial intelligence,Detector,Text detection,Mathematics | Journal |
Volume | Issue | ISSN |
102 | C | 0031-3203 |
Citations | PageRank | References |
2 | 0.37 | 0 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Siwei Wang | 1 | 40 | 13.72 |
Yudong Liu | 2 | 3 | 0.72 |
Zheqi He | 3 | 6 | 1.44 |
Yongtao Wang | 4 | 133 | 19.39 |
Zhi Tang | 5 | 256 | 53.42 |