- Task 1 - Video mode Localisation
- Task 2 - Video Mode End-to-End
- Task 3 - Still image mode Localisation
- Task 4 - Still image mode Word Recognition
- Task 5 - Still image mode End-to-End
method: google vision api2017-07-24
Authors: morimoto
Description: google vision api(private)
method: OpenCV + Tesseract2017-09-01
Authors: RRC DOST organizers
Description: Code here https://github.com/ComputerVisionCentre/RRC2015_Baseline_CV3Tess
Only modification is the minArea and maxArea parameters of the ERFilter detector (in line 92) in order to detect very small text as follows:
Ptr er_filter1 = createERFilterNM1(loadClassifierNM1("trained_classifierNM1.xml"),8,0.000015f,0.00013f,0.2f,true,0.1f);
Description Paper Source Code
Date | Method | Recall | Precision | Hmean | |||
---|---|---|---|---|---|---|---|
2017-07-24 | google vision api | 1.83% | 6.33% | 2.84% | |||
2017-09-01 | OpenCV + Tesseract | 0.01% | 0.04% | 0.01% |