method: BOE_IOT_AIBD2019-04-23

Authors: Yue Li, Guangwei Huang, TingTing Wang, BOE_IOT_AIBD

Description: Our model mainly refers to the detection method of yoloV3 with darknet53 and the connectionist text proposal network of CTPN.Besides, multi-scale training and training data augment are both used.

YOLOv3: An Incremental Improvement

An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition