Authors: Xianbiao Qi, Wenwen Yu, Ning Lu, Yihao Chen, Shaoqiong Chen, Yuan Gao, Rong Xiao
Description: Based on our detection and recognition results on Task1&2, we use a lexicon (which is built from the train data set ) to autocorrect results and use RegEx to extract key information. For every keyword (company, cash, date, and address), we use different patterns of regular expression.
1. Li, Hui, et al. "Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition." arXiv preprint arXiv:1811.00751 (2018).
2. Shi, Baoguang, et al. "Aster: An attentional scene text recognizer with flexible rectification." IEEE transactions on pattern analysis and machine intelligence (2018).
3. Vaswani, Ashish, et al. "Attention is all you need." Advances in neural information processing systems. 2017.