Japan PP OCRv3 Mobile Rec

🚀 japan_PP-OCRv3_mobile_rec

japan_PP-OCRv3_mobile_rec is a text line recognition model in the PP-OCRv3_rec series, developed by the PaddleOCR team. It's a Japan-specific model based on PP-OCRv3_mobile_rec, supporting Japanese recognition.

🚀 Quick Start

✨ Features

• High - accuracy: The model has a recognition average accuracy of 45.69%, ensuring reliable results in practical applications.
• Ultra - lightweight: With a model storage size of only 8.8 M, it is easy to deploy and use.
• Multilingual support: Supports Japanese and numeric character recognition.

📦 Installation

1. PaddlePaddle Install PaddlePaddle using pip with the following commands:

   # for CUDA11.8
   python -m pip install paddlepaddle-gpu==3.0.0 -i https://www.paddlepaddle.org.cn/packages/stable/cu118/
   
   # for CUDA12.6
   python -m pip install paddlepaddle-gpu==3.0.0 -i https://www.paddlepaddle.org.cn/packages/stable/cu126/
   
   # for CPU
   python -m pip install paddlepaddle==3.0.0 -i https://www.paddlepaddle.org.cn/packages/stable/cpu/
   

   For more details on PaddlePaddle installation, refer to the PaddlePaddle official website.
2. PaddleOCR Install the latest version of the PaddleOCR inference package from PyPI:

   python -m pip install paddleocr
   

💻 Usage Examples

Basic Usage

You can quickly test the model with a single command:

paddleocr text_recognition \
    --model_name japan_PP-OCRv3_mobile_rec \
    -i https://cdn-uploads.huggingface.co/production/uploads/681c1ecd9539bdde5ae1733c/NnQK6B5BHvbHgnx9EHBZa.png

You can also integrate the model into your project. First, download the sample image to your local machine. Then run the following code:

from paddleocr import TextRecognition
model = TextRecognition(model_name="japan_PP-OCRv3_mobile_rec")
output = model.predict(input="NnQK6B5BHvbHgnx9EHBZa.png", batch_size=1)
for res in output:
    res.print()
    res.save_to_img(save_path="./output/")
    res.save_to_json(save_path="./output/res.json")

After running, the result is as follows:

{'res': {'input_path': '/root/.paddlex/predict_input/NnQK6B5BHvbHgnx9EHBZa.png', 'page_index': None, 'rec_text': '学校が終わってから、友達と遊んじゃったの。それで、帰るのが少', 'rec_score': 0.999738335609436}}

The visualized image:

For more details on usage commands and parameter descriptions, refer to the Document.

Advanced Usage

The ability of a single model is limited. A pipeline consisting of several models can handle more complex real - world problems.

PP - OCRv3

The general OCR pipeline extracts text information from images and outputs it as strings. It has 5 modules:

• Document Image Orientation Classification Module (Optional)
• Text Image Unwarping Module (Optional)
• Text Line Orientation Classification Module (Optional)
• Text Detection Module
• Text Recognition Module

Run the following command to quickly test the OCR pipeline:

paddleocr ocr -i https://cdn-uploads.huggingface.co/production/uploads/681c1ecd9539bdde5ae1733c/yoS5sCp5dVQUAPWFQlZX8.png \
    --text_recognition_model_name japan_PP-OCRv3_mobile_rec \
    --use_doc_orientation_classify False \
    --use_doc_unwarping False \
    --use_textline_orientation True \
    --save_path ./output \
    --device gpu:0 

The results will be printed in the terminal:

{'res': {'input_path': '/root/.paddlex/predict_input/yoS5sCp5dVQUAPWFQlZX8.png', 'page_index': None, 'model_settings': {'use_doc_preprocessor': True, 'use_textline_orientation': True}, 'doc_preprocessor_res': {'input_path': None, 'page_index': None, 'model_settings': {'use_doc_orientation_classify': False, 'use_doc_unwarping': False}, 'angle': -1}, 'dt_polys': array([[[ 65,   9],
        ...,
        [ 65,  39]],

       ...,

       [[ 34, 211],
        ...,
        [ 34, 245]]], dtype=int16), 'text_det_params': {'limit_side_len': 64, 'limit_type': 'min', 'thresh': 0.3, 'max_side_limit': 4000, 'box_thresh': 0.6, 'unclip_ratio': 1.5}, 'text_type': 'general', 'textline_orientation_angles': array([0, ..., 0]), 'text_rec_score_thresh': 0.0, 'rec_texts': ['彼女のいいたいことが、正晴にもなんとなくわかった。その一時', '間というのには、重大な意味があるのだ。', 'Iもしそうしていたら」雪穂はいったん唇を噛んでから続け', 'た。「そうしていたら、たぶんおかあさんは死なずに済んだと思', 'う。それを思うと・'], 'rec_scores': array([0.98636633, ..., 0.94151145]), 'rec_polys': array([[[ 65,   9],
        ...,
        [ 65,  39]],

       ...,

       [[ 34, 211],
        ...,
        [ 34, 245]]], dtype=int16), 'rec_boxes': array([[ 65, ...,  39],
       ...,
       [ 34, ..., 245]], dtype=int16)}}

If save_path is specified, the visualization results will be saved under save_path. The visualization output:

For project integration, you can use the following code:

from paddleocr import PaddleOCR  

ocr = PaddleOCR(
    text_recognition_model_name="japan_PP-OCRv3_mobile_rec",
    use_doc_orientation_classify=False, # Use use_doc_orientation_classify to enable/disable document orientation classification model
    use_doc_unwarping=False, # Use use_doc_unwarping to enable/disable document unwarping module
    use_textline_orientation=True, # Use use_textline_orientation to enable/disable textline orientation classification model
    device="gpu:0", # Use device to specify GPU for model inference
)
result = ocr.predict("https://cdn-uploads.huggingface.co/production/uploads/681c1ecd9539bdde5ae1733c/yoS5sCp5dVQUAPWFQlZX8.png")  
for res in result:  
    res.print()  
    res.save_to_img("output")  
    res.save_to_json("output")

The default model in the pipeline is PP - OCRv5_server_rec. You need to specify japan_PP-OCRv3_mobile_rec using the text_recognition_model_name argument. You can also use a local model file with the text_recognition_model_dir argument. For more details on usage commands and parameter descriptions, refer to the Document.

📚 Documentation

The model's key accuracy metrics are as follows:

⚠️ Important Note

If any character (including punctuation) in a line was incorrect, the entire line was marked as wrong. This ensures higher accuracy in practical applications.

📄 License

This project is licensed under the Apache - 2.0 license.

🔗 Links

• PaddleOCR Repo
• PaddleOCR Documentation