method: NXB OCR2019-05-27

Authors: Yupeng Cao(X),Jie Zhang(B), Qiufeng Wang*(X),Jing Li(X), Qi Qu(B), Cheng Cheng*(N), Kaizhu Huang*(X) (Equal Contribution)

Description: A text detector based on semantic segmentation is used. It consists of EAST and PSENET, Model ensembling technique is used to increase accuracy. A CNN-based method is used for training script identification classifier in cropped word images. Using only ICDAR 2017 MLT training set and ICDAR 2019 training set.

P.S.Affiliation of Authors
(N:Institute of Nanotechnology and Nano-Bionics, Chinese Academy of Sciences ;
X:Xi’an Jiaotong-liverpool University ;
B:Beijing Babel Tenchnology Co., Ltd.)