Text Detection Module Development Tutorial¶

I. Overview¶

The text detection module is a crucial component in OCR (Optical Character Recognition) systems, responsible for locating and marking regions containing text within images. The performance of this module directly impacts the accuracy and efficiency of the entire OCR system. The text detection module typically outputs bounding boxes for text regions, which are then passed on to the text recognition module for further processing.

II. Supported Models¶

Model	Model Download Link	Detection Hmean (%)	GPU Inference Time (ms) [Normal Mode / High-Performance Mode]	CPU Inference Time (ms) [Normal Mode / High-Performance Mode]	Model Size (M)	Description
PP-OCRv4_server_det	Inference Model/Trained Model	82.69	83.34 / 80.91	442.58 / 442.58	109	The server-side text detection model of PP-OCRv4, featuring higher accuracy and suitable for deployment on high-performance servers
PP-OCRv4_mobile_det	Inference Model/Trained Model	77.79	8.79 / 3.13	51.00 / 28.58	4.7	The mobile text detection model of PP-OCRv4, optimized for efficiency and suitable for deployment on edge devices

Test Environment Description:

Performance Test Environment
Test Dataset: PaddleOCR Self-built Dataset for Chinese and English, Covering Various Scenarios
Hardware Configuration:
- GPU: NVIDIA Tesla T4
- CPU: Intel Xeon Gold 6271C @ 2.60GHz
- Other Environments: Ubuntu 20.04 / cuDNN 8.6 / TensorRT 8.5.2.2
Inference Mode Description

Mode	GPU Configuration	CPU Configuration	Acceleration Technology Combination
Normal Mode	FP32 Precision / No TRT Acceleration	FP32 Precision / 8 Threads	PaddleInference
High-Performance Mode	Optimal combination of pre-selected precision types and acceleration strategies	FP32 Precision / 8 Threads	Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.)

III. Quick Integration¶

❗ Before quick integration, please install the PaddleX wheel package. For detailed instructions, refer to the PaddleX Local Installation Guide.

Just a few lines of code can complete the inference of the text detection module, allowing you to easily switch between models under this module. You can also integrate the model inference of the text detection module into your project. Before running the following code, please download the demo image to your local machine.

from paddlex import create_model
model = create_model(model_name="PP-OCRv4_mobile_det")
output = model.predict("general_ocr_001.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 obtained is:

{'res': {'input_path': 'general_ocr_001.png', "page_index": None, 'dt_polys': [[[73, 552], [453, 542], [454, 575], [74, 585]], [[17, 506], [515, 486], [517, 535], [19, 555]], [[189, 457], [398, 449], [399, 482], [190, 490]], [[41, 412], [484, 387], [486, 433], [43, 457]]], 'dt_scores': [0.7555687038101032, 0.701620896397861, 0.8839516283528792, 0.8123399529333318]}}

The meanings of the running result parameters are as follows: - input_path: Indicates the path of the input image to be predicted. - page_index: If the input is a PDF file, it indicates which page of the PDF it is; otherwise, it is None. - dt_polys: Indicates the predicted text detection boxes, where each text detection box contains four vertices of a quadrilateral. Each vertex is a tuple representing the x and y coordinates of the vertex. - dt_scores: Indicates the confidence scores of the predicted text detection boxes.

The visualization image is as follows:

Note: Due to network issues, the above URL may not be successfully parsed. If you need the content of this webpage, please check the validity of the link and try again. Alternatively, if parsing this link is not necessary for your question, please proceed with other questions.

Relevant methods, parameters, and explanations are as follows:

create_model instantiates a text detection model (here using PP-OCRv4_mobile_det as an example). The specific explanation is as follows:

Parameter	Parameter Description	Parameter Type	Options	Default Value
`model_name`	Name of the model	`str`	All text detection model names supported by PaddleX	None
`model_dir`	Path to store the model	`str`	None	None
`limit_side_len`	Limit on the side length of the detection image	`int/None`	int: Any integer greater than 0 None: If set to None, the default value from the PaddleX official model configuration will be used	None
`limit_type`	Type of side length limit for detection	`str/None`	str: Supports "min" and "max". "min" ensures the shortest side of the image is not less than `limit_side_len`, "max" ensures the longest side is not greater than `limit_side_len` None: If set to None, the default value from the PaddleX official model configuration will be used	None
`thresh`	Threshold for considering a pixel as a text pixel in the output probability map	`float/None`	float: Any float greater than 0 None: If set to None, the default value from the PaddleX official model configuration will be used	None
`box_thresh`	Threshold for considering a detected box as a text region based on the average score of pixels inside the box	`float/None`	float: Any float greater than 0 None: If set to None, the default value from the PaddleX official model configuration will be used	None
`unclip_ratio`	Expansion ratio for text regions using the Vatti clipping algorithm	`float/None`	float: Any float greater than 0 None: If set to None, the default value from the PaddleX official model configuration will be used	None

The model_name must be specified. After specifying model_name, the default model parameters built into PaddleX will be used. If model_dir is specified, the user-defined model will be used.
The predict() method of the text detection model is called for inference prediction. The parameters of the predict() method are input, batch_size, limit_side_len, limit_type, thresh, box_thresh, max_candidates, unclip_ratio, and use_dilation. The specific explanation is as follows:

Parameter	Parameter Description	Parameter Type	Options	Default Value
`input`	Data to be predicted, supporting multiple input types	`Python Var`/`str`/`dict`/`list`	Python Variable, such as image data represented by `numpy.ndarray` File Path, such as the local path of an image file: `/root/data/img.jpg` URL Link, such as the web URL of an image file: Example Local Directory, the directory should contain the data files to be predicted, such as the local path: `/root/data/` List, the elements of the list should be of the above-mentioned data types, such as `[numpy.ndarray, numpy.ndarray]`, `[\"/root/data/img1.jpg\", \"/root/data/img2.jpg\"]`, `[\"/root/data1\", \"/root/data2\"]`	None
`batch_size`	Batch size	`int`	Any integer greater than 0	1
`limit_side_len`	Limit on the side length of the detection image	`int/None`	int: Any integer greater than 0 None: If set to None, the default value from model initialization will be used	None
`limit_type`	Type of side length limit for detection	`str/None`	str: Supports "min" and "max". "min" ensures the shortest side of the image is not less than `limit_side_len`, "max" ensures the longest side is not greater than `limit_side_len` None: If set to None, the default value from model initialization will be used	None
`thresh`	Threshold for considering a pixel as a text pixel in the output probability map	`float/None`	float: Any float greater than 0 None: If set to None, the default value from model initialization will be used	None
`box_thresh`	Threshold for considering a detected box as a text region based on the average score of pixels inside the box	`float/None`	float: Any float greater than 0 None: If set to None, the default value from model initialization will be used	None
`unclip_ratio`	Expansion ratio for text regions using the Vatti clipping algorithm	`float/None`	float: Any float greater than 0 None: If set to None, the default value from model initialization will be used	None

The prediction results are processed, with each sample's prediction result being of type dict, and supporting operations such as printing, saving as an image, and saving as a json file:

Method	Method Description	Parameter	Parameter Type	Parameter Description	Default Value
`print()`	Print the result to the terminal	`format_json`	`bool`	Whether to format the output content using `JSON` indentation	`True`
		`indent`	`int`	Specify the indentation level to beautify the output `JSON` data, making it more readable. This is only effective when `format_json` is `True`	4
		`ensure_ascii`	`bool`	Control whether non-`ASCII` characters are escaped to `Unicode`. When set to `True`, all non-`ASCII` characters will be escaped; `False` retains the original characters. This is only effective when `format_json` is `True`	`False`
`save_to_json()`	Save the result as a JSON file	`save_path`	`str`	The file path for saving. When it is a directory, the saved file name will match the input file name	None
		`indent`	`int`	Specify the indentation level to beautify the output `JSON` data, making it more readable. This is only effective when `format_json` is `True`	4
		`ensure_ascii`	`bool`	Control whether non-`ASCII` characters are escaped to `Unicode`. When set to `True`, all non-`ASCII` characters will be escaped; `False` retains the original characters. This is only effective when `format_json` is `True`	`False`
`save_to_img()`	Save the result as an image file	`save_path`	`str`	The file path for saving. When it is a directory, the saved file name will match the input file name	None

Additionally, it also supports obtaining visualized images with results and prediction results through attributes, as follows:

Attribute	Attribute Description
`json`	Get the prediction result in `json` format
`img`	Get the visualized image in `dict` format

For more information on using PaddleX's single-model inference APIs, refer to the PaddleX Single Model Python Script Usage Instructions.

IV. Custom Development¶

If you seek even higher accuracy from existing models, you can leverage PaddleX's custom development capabilities to develop better text detection models. Before developing text detection models with PaddleX, ensure you have installed the PaddleOCR plugin for PaddleX. The installation process can be found in the PaddleX Local Installation Guide.

4.1 Data Preparation¶

Before model training, you need to prepare a dataset for the specific task module. PaddleX provides data validation functionality for each module, and only data that passes validation can be used for model training. Additionally, PaddleX provides demo datasets for each module, which you can use to complete subsequent development. If you wish to use private datasets for model training, refer to the PaddleX Text Detection/Text Recognition Task Module Data Annotation Tutorial.

4.1.1 Demo Data Download¶

You can use the following commands to download the demo dataset to a specified folder:

wget https://paddle-model-ecology.bj.bcebos.com/paddlex/data/ocr_det_dataset_examples.tar -P ./dataset
tar -xf ./dataset/ocr_det_dataset_examples.tar -C ./dataset/

4.1.2 Data Validation¶

A single command can complete data validation:

python main.py -c paddlex/configs/modules/text_detection/PP-OCRv4_mobile_det.yaml \
    -o Global.mode=check_dataset \
    -o Global.dataset_dir=./dataset/ocr_det_dataset_examples

After executing the above command, PaddleX will validate the dataset and gather basic information about it. Once the command runs successfully, Check dataset passed ! will be printed in the log. The validation result file is saved in ./output/check_dataset_result.json, and related outputs will be stored in the ./output/check_dataset directory in the current directory. The output directory includes sample images and histograms of sample distribution.

👉 Validation Result Details (Click to Expand)

The specific content of the validation result file is:

{
  "done_flag": true,
  "check_pass": true,
  "attributes": {
    "train_samples": 200,
    "train_sample_paths": [
      "../dataset/ocr_det_dataset_examples/images/train_img_61.jpg",
      "../dataset/ocr_det_dataset_examples/images/train_img_289.jpg"
    ],
    "val_samples": 50,
    "val_sample_paths": [
      "../dataset/ocr_det_dataset_examples/images/val_img_61.jpg",
      "../dataset/ocr_det_dataset_examples/images/val_img_137.jpg"
    ]
  },
  "analysis": {
    "histogram": "check_dataset/histogram.png"
  },
  "dataset_path": "./dataset/ocr_det_dataset_examples",
  "show_type": "image",
  "dataset_type": "TextDetDataset"
}

In the above validation result, check_pass being true indicates that the dataset format meets the requirements. The explanation of other metrics is as follows:

attributes.train_samples: The number of training samples in the dataset is 200;
attributes.val_samples: The number of validation samples in the dataset is 50;
attributes.train_sample_paths: List of relative paths for visualizing training sample images in the dataset;
attributes.val_sample_paths: List of relative paths for visualizing validation sample images in the dataset;

Additionally, the dataset validation also analyzed the distribution of the length and width of all images in the dataset and plotted a distribution histogram (histogram.png):

4.1.3 Dataset Format Conversion/Dataset Splitting (Optional)¶

After completing data validation, you can convert the dataset format and re-split the training/validation ratio by modifying the configuration file or appending hyperparameters.

👉 Details on Format Conversion/Dataset Splitting (Click to Expand)

(1) Dataset Format Conversion

Text detection does not support data format conversion.

(2) Dataset Splitting

The parameters for dataset splitting can be set by modifying the CheckDataset section in the configuration file. Below are some example explanations for the parameters in the configuration file:

CheckDataset:
split:
enable: Whether to re-split the dataset. Set to True to enable dataset splitting, default is False;
train_percent: If re-splitting the dataset, set the percentage of the training set. The type is any integer between 0-100, and the sum with val_percent must be 100;

For example, if you want to re-split the dataset with a 90% training set and a 10% validation set, modify the configuration file as follows:

......
CheckDataset:
  ......
  split:
    enable: True
    train_percent: 90
    val_percent: 10
  ......

Then execute the command:

python main.py -c paddlex/configs/modules/text_detection/PP-OCRv4_mobile_det.yaml \
    -o Global.mode=check_dataset \
    -o Global.dataset_dir=./dataset/ocr_det_dataset_examples

After dataset splitting, the original annotation files will be renamed to xxx.bak in the original path.

The above parameters can also be set by appending command-line arguments:

python main.py -c paddlex/configs/modules/text_detection/PP-OCRv4_mobile_det.yaml  \
    -o Global.mode=check_dataset \
    -o Global.dataset_dir=./dataset/ocr_det_dataset_examples \
    -o CheckDataset.split.enable=True \
    -o CheckDataset.split.train_percent=90 \
    -o CheckDataset.split.val_percent=10

4.2 Model Training¶

Model training can be completed with a single command. Here's an example of training the PP-OCRv4 mobile text detection model (PP-OCRv4_mobile_det):

python main.py -c paddlex/configs/modules/text_detection/PP-OCRv4_mobile_det.yaml \
    -o Global.mode=train \
    -o Global.dataset_dir=./dataset/ocr_det_dataset_examples

The steps required are:

Specify the path to the model's .yaml configuration file (here it's PP-OCRv4_mobile_det.yaml,When training other models, you need to specify the corresponding configuration files. The relationship between the model and configuration files can be found in the PaddleX Model List (CPU/GPU))
Set the mode to model training: -o Global.mode=train
Specify the path to the training dataset: -o Global.dataset_dir Other related parameters can be set by modifying the Global and Train fields in the .yaml configuration file or adjusted by appending parameters in the command line. For example, to specify training on the first two GPUs: -o Global.device=gpu:0,1; to set the number of training epochs to 10: -o Train.epochs_iters=10. For more modifiable parameters and their detailed explanations, refer to the PaddleX Common Configuration Parameters Documentation.

👉 More Information (Click to Expand)

During model training, PaddleX automatically saves the model weight files, with the default being output. If you need to specify a save path, you can set it through the -o Global.output field in the configuration file.
PaddleX shields you from the concepts of dynamic graph weights and static graph weights. During model training, both dynamic and static graph weights are produced, and static graph weights are selected by default for model inference.
After completing the model training, all outputs are saved in the specified output directory (default is ./output/), typically including:
train_result.json: Training result record file, recording whether the training task was completed normally, as well as the output weight metrics, related file paths, etc.;
train.log: Training log file, recording changes in model metrics and loss during training;
config.yaml: Training configuration file, recording the hyperparameter configuration for this training session;
.pdparams, .pdema, .pdopt.pdstate, .pdiparams, .pdmodel: Model weight-related files, including network parameters, optimizer, EMA, static graph network parameters, static graph network structure, etc.;

4.3 Model Evaluation¶

After completing model training, you can evaluate the specified model weight file on the validation set to verify the model's accuracy. Using PaddleX for model evaluation can be done with a single command:

python main.py -c paddlex/configs/modules/text_detection/PP-OCRv4_mobile_det.yaml \
    -o Global.mode=evaluate \
    -o Global.dataset_dir=./dataset/ocr_det_dataset_examples

Similar to model training, the following steps are required:

Specify the path to the model's .yaml configuration file (in this case, PP-OCRv4_mobile_det.yaml)
Specify the mode as model evaluation: -o Global.mode=evaluate
Specify the path to the validation dataset: -o Global.dataset_dir

Other related parameters can be set by modifying the fields under Global and Evaluate in the .yaml configuration file. For details, please refer to PaddleX General Model Configuration File Parameter Instructions.

👉 More Instructions (Click to Expand)

During model evaluation, you need to specify the path to the model weight file. Each configuration file has a built-in default weight save path. If you need to change it, you can set it by adding a command line argument, such as -o Evaluate.weight_path=./output/best_accuracy/best_accuracy.pdparams.

After completing the model evaluation, an evaluate_result.json will be generated, which records the evaluation results. Specifically, it records whether the evaluation task was completed successfully and the model's evaluation metrics, including precision, recall, and hmean.

4.4 Model Inference and Model Integration¶

After completing model training and evaluation, you can use the trained model weights for inference predictions or Python integration.

4.4.1 Model Inference¶

To perform inference predictions via the command line, simply use the following command. Before running the following code, please download the demo image to your local machine.

python main.py -c paddlex/configs/modules/text_detection/PP-OCRv4_mobile_det.yaml \
    -o Global.mode=predict \
    -o Predict.model_dir="./output/best_accuracy/inference" \
    -o Predict.input="general_ocr_001.png"

Similar to model training and evaluation, the following steps are required:

Specify the .yaml configuration file path of the model (here it's PP-OCRv4_mobile_det.yaml)
Set the mode to model inference prediction: -o Global.mode=predict
Specify the model weights path: -o Predict.model_dir="./output/best_accuracy/inference"
Specify the input data path: -o Predict.input="..." Other related parameters can be set by modifying the fields under Global and Predict in the .yaml configuration file. For details, refer to PaddleX Common Model Configuration File Parameter Description.
Alternatively, you can use the PaddleX wheel package for inference, easily integrating the model into your own projects.

4.4.2 Model Integration¶

Models can be directly integrated into PaddleX pipelines or into your own projects.

1.Pipeline Integration

The text detection module can be integrated into PaddleX pipelines such as the General OCR Pipeline, Table Recognition Pipeline, and PP-ChatOCRv3-doc. Simply replace the model path to update the text detection module of the relevant pipeline.

2.Module Integration

The model weights you produce can be directly integrated into the text detection module. Refer to the Python example code in Quick Integration, and simply replace the model with the path to your trained model.

You can also use the PaddleX high-performance inference plugin to optimize the inference process of your model and further improve efficiency. For detailed procedures, please refer to the PaddleX High-Performance Inference Guide.