LDRNet is lightweight deep neural network for localizing document in a image/photo with extremely low latency. Given any image as input, LDRNet predicts the coordinates of the document's quadrilateral corners in real-time.
- tensorflow==2.3.1
- tensorflow-addons==0.11.2
- opencv-python==4.4.0.46
- numpy==1.18.5
A simple example for predicting the quadrilateral corners of the image in imgs folder:
python3 predict.py
CUDA_VSIBLE_DEVICES=0 python3 train.py --config_file ./config.yaml
- fill the label_path and img_folder_path in config.yaml
- label consists of 18 elements: file name, eights floats for four coordinates, eights float for weights(set to 0.0625), class index(start from 0)
- To TensorRT
- To TNN
If you publish work related to LDRNet or Real-time Document Localization, please refer to the following paper and cite accordingly:
@inproceedings{wu2023ldrnet,
title={LDRNet: Enabling Real-time Document Localization on Mobile Devices},
author={Wu, Han and Qian, Holland and Wu, Huaming and van Moorsel, Aad},
booktitle={Machine Learning and Principles and Practice of Knowledge Discovery in Databases: International Workshops of ECML PKDD 2022, Grenoble, France, September 19--23, 2022, Proceedings, Part I},
pages={618--629},
year={2023},
organization={Springer}
}