Authors: Youngmin Baek, Bado Lee, Dongyoon Han, Sangdoo Yun, and Hwalsuk Lee
Description: We propose 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.
Authors: Jaemyung Lee, Jusung Lee, Younghyun Lee, Joonsoo Lee
Description: This work was supported by Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government(MSIT) (No.1711097855, Text Localization and Recognition for Efficient Digital Contents Analysis)