method: pursuer2019-04-30
Authors: Mengbiao Zhao, Wei Feng, Jiangpeng Wan, Fei Yin, Chenglin Liu
Description: We are from Institute of Automation, Chinese Academy of Sciences. We follow the work of Deep Direct Regression for Multi-Oriented Scene Text Detection, Wenhao He, Xu-Yao Zhang, Fei Yin, Cheng-Lin Liu, https://arxiv.org/abs/1703.08289. This framework is based on fully convolutional network with a bi-task prediction module, in which one is a pixel-wise classification between the text and non-text and the other is pixel-wise regression to determine the vertex coordinates of quadrilateral text boundaries.