The picture above is the result of our Ultra-lightweight Chinese OCR model. For more testing results, please see the end of the article [Ultra-lightweight Chinese OCR results](#Ultra-lightweight-Chinese-OCR-results) and [General Chinese OCR results](#General-Chinese-OCR-results).
*If wget is not installed in the windows system, you can copy the link to the browser to download the model. After model downloaded, unzip it and place it in the corresponding directory*
The following code implements text detection and recognition inference tandemly. When performing prediction, you need to specify the path of a single image or image folder through the parameter `image_dir`, the parameter `det_model_dir` specifies the path to detection model, and the parameter `rec_model_dir` specifies the path to the recognition model. The visual prediction results are saved to the `./inference_results` folder by default.
To run inference of the Generic Chinese OCR model, follow these steps above to download the corresponding models and update the relevant parameters. Examples are as follows:
For use of [LSVT](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/doc/datasets.md#1icdar2019-lsvt) street view dataset with a total of 3w training data，the related configuration and pre-trained models for Chinese detection task are as follows:
* Note: For the training and evaluation of the above DB model, post-processing parameters box_thresh=0.6 and unclip_ratio=1.5 need to be set. If using different datasets and different models for training, these two parameters can be adjusted for better result.
For the training guide and use of PaddleOCR text detection algorithms, please refer to the document [Text detection model training/evaluation/prediction](./doc/detection.md)
Refer to [DTRB](https://arxiv.org/abs/1904.01906), the training and evaluation result of these above text recognition (using MJSynth and SynthText for training, evaluate on IIIT, SVT, IC03, IC13, IC15, SVTP, CUTE) is as follow:
We use [LSVT](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/doc/datasets.md#1icdar2019-lsvt) dataset and cropout 30w traning data from original photos by using position groundtruth and make some calibration needed. In addition, based on the LSVT corpus, 500w synthetic data is generated to train the Chinese model. The related configuration and pre-trained models are as follows:
|Ultra-lightweight Chinese model|MobileNetV3|rec_chinese_lite_train.yml|[Download link](https://paddleocr.bj.bcebos.com/ch_models/ch_rec_mv3_crnn.tar)|
|General Chinese OCR model|Resnet34_vd|rec_chinese_common_train.yml|[Download link](https://paddleocr.bj.bcebos.com/ch_models/ch_rec_r34_vd_crnn.tar)|
Please refer to the document for training guide and use of PaddleOCR text recognition algorithms [Text recognition model training/evaluation/prediction](./doc/recognition.md)
The inference of recognition model based on attention loss is still being debugged. For Chinese text recognition, it is recommended to choose the recognition model based on CTC loss first. In practice, it is also found that the recognition model based on attention loss is not as effective as the one based on CTC loss.
When there are a lot of texts in the picture, the prediction time will increase. You can use `--rec_batch_num` to set a smaller prediction batch size. The default value is 30, which can be changed to 10 or other values.
It is expected that the service deployment based on Serving and the mobile deployment based on Paddle Lite will be released successively in mid-to-late June. Stay tuned for more updates.
title={EAST: an efficient and accurate scene text detector},
author={Zhou, Xinyu and Yao, Cong and Wen, He and Wang, Yuzhi and Zhou, Shuchang and He, Weiran and Liang, Jiajun},
booktitle={Proceedings of the IEEE conference on Computer Vision and Pattern Recognition},
pages={5551--5560},
year={2017}
}
2. DB:
@article{liao2019real,
title={Real-time Scene Text Detection with Differentiable Binarization},
author={Liao, Minghui and Wan, Zhaoyi and Yao, Cong and Chen, Kai and Bai, Xiang},
journal={arXiv preprint arXiv:1911.08947},
year={2019}
}
3. DTRB:
@inproceedings{baek2019wrong,
title={What is wrong with scene text recognition model comparisons? dataset and model analysis},
author={Baek, Jeonghun and Kim, Geewook and Lee, Junyeop and Park, Sungrae and Han, Dongyoon and Yun, Sangdoo and Oh, Seong Joon and Lee, Hwalsuk},
booktitle={Proceedings of the IEEE International Conference on Computer Vision},
pages={4715--4723},
year={2019}
}
4. SAST:
@inproceedings{wang2019single,
title={A Single-Shot Arbitrarily-Shaped Text Detector based on Context Attended Multi-Task Learning},
author={Wang, Pengfei and Zhang, Chengquan and Qi, Fei and Huang, Zuming and En, Mengyi and Han, Junyu and Liu, Jingtuo and Ding, Errui and Shi, Guangming},
booktitle={Proceedings of the 27th ACM International Conference on Multimedia},
pages={1277--1285},
year={2019}
}
5. SRN:
@article{yu2020towards,
title={Towards Accurate Scene Text Recognition with Semantic Reasoning Networks},
author={Yu, Deli and Li, Xuan and Zhang, Chengquan and Han, Junyu and Liu, Jingtuo and Ding, Errui},
journal={arXiv preprint arXiv:2003.12294},
year={2020}
}
6. end2end-psl:
@inproceedings{sun2019chinese,
title={Chinese Street View Text: Large-scale Chinese Text Reading with Partially Supervised Learning},
author={Sun, Yipeng and Liu, Jiaming and Liu, Wei and Han, Junyu and Ding, Errui and Liu, Jingtuo},
booktitle={Proceedings of the IEEE International Conference on Computer Vision},
