Abstract | ||
---|---|---|
Scene text detection plays an important role in many real-world applications. In this paper, we propose a multi-oriented scene text detection framework, which includes three main modules. We utilize a deep residual network in the front of the framework to learn text representations. A set of fixed-width, multi-ratio rotation anchors is introduced to slide over convolutional feature maps and generate the text proposals with orientation information. An in-network recurrent architecture is then seamlessly connected, where the sequential context of proposals is encoded in order to facilitate the construction of text lines. Extensive experiments are conducted on two ICDAR benchmarks to demonstrate the effectiveness of our approach. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1016/j.compeleceng.2021.107428 | COMPUTERS & ELECTRICAL ENGINEERING |
Keywords | DocType | Volume |
Scene text detection, Rotation anchors, Residual network, Context information | Journal | 95 |
ISSN | Citations | PageRank |
0045-7906 | 0 | 0.34 |
References | Authors | |
0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Beiji Zou | 1 | 0 | 1.01 |
Wenjun Yang | 2 | 0 | 2.37 |
Shu Liu | 3 | 1 | 1.03 |
Lingzi Jiang | 4 | 0 | 0.34 |