Latin PP OCRv3 Mobile Rec

🚀 latin_PP-OCRv3_mobile_rec

latin_PP-OCRv3_mobile_rec is a text line recognition model developed by the PaddleOCR team. It's part of the PP-OCRv3_rec series, specifically trained for Latin recognition based on the PP-OCRv3_mobile_rec model. This model offers high accuracy and efficiency for Latin text recognition tasks.

🚀 Quick Start

📦 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's functionality with a single command:

paddleocr text_recognition \
    --model_name latin_PP-OCRv3_mobile_rec \
    -i https://cdn-uploads.huggingface.co/production/uploads/681c1ecd9539bdde5ae1733c/az8vEPS1Q3718b3D0ehNj.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="latin_PP-OCRv3_mobile_rec")
output = model.predict(input="az8vEPS1Q3718b3D0ehNj.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/az8vEPS1Q3718b3D0ehNj.png', 'page_index': None, 'rec_text': 'Latini multilinearis', 'rec_score': 0.9983808398246765}}

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

🌟 Advanced Usage - Pipeline Usage

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

PP-OCRv3 Pipeline

The general OCR pipeline extracts text information from images and outputs it in string format. It consists of 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 experience the OCR pipeline:

paddleocr ocr -i https://cdn-uploads.huggingface.co/production/uploads/681c1ecd9539bdde5ae1733c/E-CtmA3e9B1yfBqLJOXMj.png \
    --text_recognition_model_name latin_PP-OCRv3_mobile_rec \
    --use_doc_orientation_classify False \
    --use_doc_unwarping False \
    --use_textline_orientation True \
    --save_path ./output \
    --device gpu:0 

The result will be printed to the terminal:

{'res': {'input_path': '/root/.paddlex/predict_input/E-CtmA3e9B1yfBqLJOXMj.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([[[ 11,   5],
        ...,
        [ 11,  33]],

       ...,

       [[ 11,  78],
        ...,
        [ 11, 102]]], 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': ['Exemplum', 'probationis textus', 'Latini multilinearis'], 'rec_scores': array([0.99786115, ..., 0.99657601]), 'rec_polys': array([[[ 11,   5],
        ...,
        [ 11,  33]],

       ...,

       [[ 11,  78],
        ...,
        [ 11, 102]]], dtype=int16), 'rec_boxes': array([[ 11, ...,  33],
       ...,
       [ 11, ..., 102]], dtype=int16)}}

For project integration, you can use the following code:

from paddleocr import PaddleOCR  

ocr = PaddleOCR(
    text_recognition_model_name="latin_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/E-CtmA3e9B1yfBqLJOXMj.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 can specify latin_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, refer to the Document.

✨ Features

The latin_PP-OCRv3_mobile_rec model has the following features:

⚠️ 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.

📚 Documentation

• PaddleOCR Repo
• PaddleOCR Documentation

📄 License

This project is licensed under the Apache-2.0 license.