Create a python sample with [EAST: An Efficient and Accurate Scene Text Detector](https://arxiv.org/abs/1704.03155v2) c++ implementation: https://github.com/opencv/opencv/blob/master/samples/dnn/text_detection.cpp There are [cv::RotatedRect](https://docs.opencv.org/master/db/dd6/classcv_1_1RotatedRect.html) and [cv::dnn::NMSBoxes](https://docs.opencv.org/master/d6/d0f/group__dnn.html#gaeec27cb32195e71e6d88032bda193162) that should be properly wrapped.