Abstract | ||
---|---|---|
The reading of arbitrarily-shaped text has received increasing research attention. However, existing text spotters are mostly built on two-stage frameworks or character-based methods, which suffer from either Non-Maximum Suppression (NMS), Region-of-Interest (Rot) operations, or character-level annotations. In this paper, to address the above problems, we propose a novel fully convolutional Point Gathering Network (PGNet) for reading arbitrarily-shaped text in real-time. The PGNet is a single-shot text spotter, where the pixel-level character classification map is learned with proposed PG-CTC loss avoiding the usage of character-level annotations. With a PG-CTC decoder, we gather high-level character classification vectors from two-dimensional space and decode them into text symbols without NMS and Rot operations involved, which guarantees high efficiency. Additionally, reasoning the relations between each character and its neighbors, a graph refinement module (GRM) is proposed to optimize the coarse recognition and improve the end-to-end performance. Experiments prove that the proposed method achieves competitive accuracy, meanwhile significantly improving the running speed. In particular, in Total-Text, it runs at 46.7 FPS, surpassing the previous spotters with a large margin. |
Year | Venue | DocType |
---|---|---|
2021 | THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE | Conference |
Volume | ISSN | Citations |
35 | 2159-5399 | 0 |
PageRank | References | Authors |
0.34 | 0 | 10 |
Name | Order | Citations | PageRank |
---|---|---|---|
Pengfei Wang | 1 | 2 | 0.76 |
Chengquan Zhang | 2 | 138 | 7.38 |
Fei Qi | 3 | 2 | 0.76 |
Shanshan Liu | 4 | 0 | 0.34 |
Xiaoqiang Zhang | 5 | 0 | 0.34 |
Pengyuan Lyu | 6 | 0 | 0.34 |
Junyu Han | 7 | 85 | 11.12 |
jingtuo liu | 8 | 47 | 9.43 |
Er-rui Ding | 9 | 142 | 29.31 |
Guangming Shi | 10 | 2663 | 184.81 |