Method: A two-stage text detector based on cascade rcnn(using total 10000 images of mlt19) - Task 1 - Text Localization - ICDAR 2019 Robust Reading Challenge on Multi-lingual scene text detection and recognition

method: A two-stage text detector based on cascade rcnn(using total 10000 images of mlt19)2019-06-02

Authors: Yudong Liu, Yongtao Wang

Description: We modify the regression of cascade rcnn at the third stage, we train with 9000 images of mlt19 data.The rest 1000 images are used for validation. Multi scale and large model are used.

@inproceedings{cai2018cascade, title={Cascade r-cnn: Delving into high quality object detection}, author={Cai, Zhaowei and Vasconcelos, Nuno}, booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition}, pages={6154--6162}, year={2018} }

Source code