Efficient and Accurate Arbitrary-Shaped Text Detection With Pixel Aggregation Network
Tongji University · Nanjing University · +5 more institutions
Abstract
Scene text detection, an important step of scene text reading systems, has witnessed rapid development with convolutional neural networks. Nonetheless, two main challenges still exist and hamper its deployment to real-world applications. The first problem is the trade-off between speed and accuracy. The second one is to model the arbitrary-shaped text instance. Recently, some methods have been proposed to tackle arbitrary-shaped text detection, but they rarely take the speed of the entire pipeline into consideration, which may fall short in practical applications. In this paper, we propose an efficient and accurate arbitrary-shaped text detector, termed Pixel Aggregation Network (PAN), which is equipped with a…
Citation impact
- FWCI
- 24.60
- Percentile
- 100%
- References
- 80
Authors
8- WWWenhai WangCorresponding
Tongji University, Nanjing University, Novel (United States)
- EXEnze Xie
Tongji University, Vi Technology (United States)
- XSXiaoge Song
Nanjing University, Novel (United States)
- YZYuhang Zang
University of Electronic Science and Technology of China
- WWWenjia Wang
Nanjing University, Tongji University
Topics & keywords
- Computer science
- Segmentation
- Pyramid (geometry)
- Pipeline (software)
- Pixel
- Feature (linguistics)
- Aggregate (composite)
- Artificial intelligence
- Quality Education