Robust ReadingCompetition
Challenges

method: NLPR-PAL2017-06-29

Authors: Wenhao He, Fei Yin, Cheng-Lin Liu

Description: this method is based on [1]. We also use images of Chinese and Japanese and Korean from the MLT competition.
[1] Deep Direct Regression for Multi-Oriented Scene Text Detection. arXiv:1703.08289

method: SCUT-DLVClab2017-06-28

Authors: Yuliang Liu, Sheng Zhang, Lianwen Jin

Description: A CNN based method.

method: google_vision_api2017-07-31

Authors: morimoto

Description: google_vision_api(private)

Ranking Table

Description Paper Source Code
DateMethodRecallPrecisionHmean
2017-06-29NLPR-PAL16.25%38.10%22.78%
2017-06-28SCUT-DLVClab11.60%46.41%18.56%
2017-07-31google_vision_api4.09%14.67%6.40%
2017-09-01OpenCV + Tesseract1.55%7.95%2.60%

Ranking Graphic