method: Clova OCR2019-05-10

Authors: Seung Shin, Sungrae Park, Seonghyeon Kim, Jaeheung Surh, Junyeop Lee, Hwalsuk Lee

Description: We used a novel text detector called CRAFT. The proposed method effectively detects text area by exploring each character and affinity between characters. To overcome the lack of individual character level annotations, our framework exploits the pseudo character-level bounding boxes acquired by the learned interim model in a weakly-supervised manner.