---
comments: true
---
# Text Recognition Module Development Tutorial
## I. Overview
The text recognition module is the core component of an OCR (Optical Character Recognition) system, responsible for extracting text information from text regions within images. The performance of this module directly impacts the accuracy and efficiency of the entire OCR system. The text recognition module typically receives bounding boxes of text regions output by the text detection module as input. Through complex image processing and deep learning algorithms, it converts the text in images into editable and searchable electronic text. The accuracy of text recognition results is crucial for subsequent applications such as information extraction and data mining.
## II. Supported Model List
| Model | Model Download Link |
Recognition Avg Accuracy(%) |
GPU Inference Time (ms) |
CPU Inference Time (ms) |
Model Size (M) |
Description |
| PP-OCRv4_mobile_rec | Inference Model/Trained Model |
78.20 |
7.95018 |
46.7868 |
10.6 M |
PP-OCRv4, developed by Baidu's PaddlePaddle Vision Team, is the next version of the PP-OCRv3 text recognition model. By introducing data augmentation schemes, GTC-NRTR guidance branches, and other strategies, it further improves text recognition accuracy without compromising model inference speed. The model offers both server and mobile versions to meet industrial needs in different scenarios. |
| PP-OCRv4_server_rec | Inference Model/Trained Model |
79.20 |
7.19439 |
140.179 |
71.2 M |
Note: The evaluation set for the above accuracy metrics is PaddleOCR's self-built Chinese dataset, covering street scenes, web images, documents, handwriting, and more, with 1.1w images for text recognition. GPU inference time for all models is based on an NVIDIA Tesla T4 machine with FP32 precision. CPU inference speed is based on an Intel(R) Xeon(R) Gold 5117 CPU @ 2.00GHz with 8 threads and FP32 precision.
> โ The above list features the 2 core models that the image classification module primarily supports. In total, this module supports 4 models. The complete list of models is as follows:
๐Model List Details
| Model | Model Download Link |
Recognition Avg Accuracy(%) |
GPU Inference Time (ms) |
CPU Inference Time (ms) |
Model Size (M) |
Description |
| PP-OCRv4_mobile_rec | Inference Model/Trained Model |
78.20 |
7.95018 |
46.7868 |
10.6 M |
PP-OCRv4, developed by Baidu's PaddlePaddle Vision Team, is the next version of the PP-OCRv3 text recognition model. By introducing data augmentation schemes, GTC-NRTR guidance branches, and other strategies, it further improves text recognition accuracy without compromising model inference speed. The model offers both server and mobile versions to meet industrial needs in different scenarios. |
| PP-OCRv4_server_rec | Inference Model/Trained Model |
79.20 |
7.19439 |
140.179 |
71.2 M |
Note: The evaluation set for the above accuracy metrics is PaddleOCR's self-built Chinese dataset, covering street scenes, web images, documents, handwriting, and more, with 1.1w images for text recognition. GPU inference time for all models is based on an NVIDIA Tesla T4 machine with FP32 precision. CPU inference speed is based on an Intel(R) Xeon(R) Gold 5117 CPU @ 2.00GHz with 8 threads and FP32 precision.
| Model | Model Download Link |
Recognition Avg Accuracy(%) |
GPU Inference Time (ms) |
CPU Inference Time |
Model Size (M) |
Description |
| ch_SVTRv2_rec | Inference Model/Trained Model |
68.81 |
8.36801 |
165.706 |
73.9 M |
SVTRv2, a server-side text recognition model developed by the OpenOCR team at the Vision and Learning Lab (FVL) of Fudan University, also won first place in the OCR End-to-End Recognition Task of the PaddleOCR Algorithm Model Challenge. Its A-rank end-to-end recognition accuracy is 6% higher than PP-OCRv4.
|
Note: The evaluation set for the above accuracy metrics is the OCR End-to-End Recognition Task of the PaddleOCR Algorithm Model Challenge - Track 1 A-rank. GPU inference time for all models is based on an NVIDIA Tesla T4 machine with FP32 precision. CPU inference speed is based on an Intel(R) Xeon(R) Gold 5117 CPU @ 2.00GHz with 8 threads and FP32 precision.
| Model | Model Download Link |
Recognition Avg Accuracy(%) |
GPU Inference Time (ms) |
CPU Inference Time |
Model Size (M) |
Description |
| ch_RepSVTR_rec | Inference Model/Trained Model |
65.07 |
10.5047 |
51.5647 |
22.1 M |
RepSVTR, a mobile text recognition model based on SVTRv2, won first place in the OCR End-to-End Recognition Task of the PaddleOCR Algorithm Model Challenge. Its B-rank end-to-end recognition accuracy is 2.5% higher than PP-OCRv4, with comparable inference speed. |
Note: The evaluation set for the above accuracy metrics is the OCR End-to-End Recognition Task of the PaddleOCR Algorithm Model Challenge - Track 1 B-rank. GPU inference time for all models is based on an NVIDIA Tesla T4 machine with FP32 precision. CPU inference speed is based on an Intel(R) Xeon(R) Gold 5117 CPU @ 2.00GHz with 8 threads and FP32 precision.
๐ Validation Result Details (Click to Expand)
The specific content of the validation result file is:
{
"done_flag": true,
"check_pass": true,
"attributes": {
"train_samples": 4468,
"train_sample_paths": [
"../dataset/ocr_rec_dataset_examples/images/train_word_1.png",
"../dataset/ocr_rec_dataset_examples/images/train_word_10.png"
],
"val_samples": 2077,
"val_sample_paths": [
"../dataset/ocr_rec_dataset_examples/images/val_word_1.png",
"../dataset/ocr_rec_dataset_examples/images/val_word_10.png"
]
},
"analysis": {
"histogram": "check_dataset/histogram.png"
},
"dataset_path": "./dataset/ocr_rec_dataset_examples",
"show_type": "image",
"dataset_type": "MSTextRecDataset"
}
In the above validation result, check_pass being true indicates that the dataset format meets the requirements. Explanations for other indicators are as follows:
attributes.train_samples: The number of training set samples in this dataset is 4468;attributes.val_samples: The number of validation set samples in this dataset is 2077;attributes.train_sample_paths: A list of relative paths to the visualized training set samples in this dataset;attributes.val_sample_paths: A list of relative paths to the visualized validation set samples in this dataset;
Additionally, the dataset validation also analyzes the distribution of character length ratios in the dataset and generates a distribution histogram (histogram.png):
๐ Dataset Format Conversion/Dataset Splitting Details (Click to Expand)
(1) Dataset Format Conversion
Text recognition does not currently support data conversion.
(2) Dataset Splitting
The parameters for dataset splitting can be set by modifying the CheckDataset section in the configuration file. Examples of some parameters in the configuration file are as follows:
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 it must sum up to 100 with val_percent;
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/text_recognition/PP-OCRv4_mobile_rec.yaml \
-o Global.mode=check_dataset \
-o Global.dataset_dir=./dataset/ocr_rec_dataset_examples
After data splitting, the original annotation files will be renamed to xxx.bak in the original path.
The above parameters also support setting through appending command line arguments:
python main.py -c paddlex/configs/text_recognition/PP-OCRv4_mobile_rec.yaml \
-o Global.mode=check_dataset \
-o Global.dataset_dir=./dataset/ocr_rec_dataset_examples \
-o CheckDataset.split.enable=True \
-o CheckDataset.split.train_percent=90 \
-o CheckDataset.split.val_percent=10
๐ 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.;
๐ More Information (Click to Expand)
When evaluating the model, you need to specify the model weights file path. Each configuration file has a default weight save path. If you need to change it, simply append the command line parameter to set it, such as -o Evaluate.weight_path=./output/best_model/best_model.pdparams.
After completing the model evaluation, an evaluate_result.json file will be produced, which records the evaluation results, specifically, whether the evaluation task was completed successfully and the model's evaluation metrics, including accใnorm_edit_dis๏ผ