comments: true

General Table Recognition Pipeline Tutorial

1. Introduction to the General Table Recognition Pipeline

Table recognition is a technology that automatically identifies and extracts table content and its structure from documents or images. It is widely used in data entry, information retrieval, and document analysis. By leveraging computer vision and machine learning algorithms, table recognition can convert complex table information into editable formats, facilitating further data processing and analysis for users.

The General Table Recognition Pipeline comprises modules for table structure recognition, layout analysis, text detection, and text recognition. If you prioritize model accuracy, choose a model with higher accuracy. If you prioritize inference speed, select a model with faster inference. If you prioritize model size, choose a model with a smaller storage footprint.

👉Model List Details

Table Recognition Module Models:

Model	Model Download Link	Accuracy (%)	CPU Inference Time (ms) [Normal Mode / High-Performance Mode]	CPU Inference Time (ms) [Normal Mode / High-Performance Mode]	Model Size (M)	Description
SLANet	Inference Model/Trained Model	59.52	103.08 / 103.08	197.99 / 197.99	6.9 M	SLANet is a table structure recognition model developed by Baidu PaddleX Team. The model significantly improves the accuracy and inference speed of table structure recognition by adopting a CPU-friendly lightweight backbone network PP-LCNet, a high-low-level feature fusion module CSP-PAN, and a feature decoding module SLA Head that aligns structural and positional information.
SLANet_plus	Inference Model/Trained Model	63.69	140.29 / 140.29	195.39 / 195.39	6.9 M	SLANet_plus is an enhanced version of SLANet, a table structure recognition model developed by Baidu PaddleX Team. Compared to SLANet, SLANet_plus significantly improves its recognition capabilities for wireless and complex tables, while reducing the model's sensitivity to the accuracy of table localization. Even when there are offsets in table localization, it can still perform relatively accurate recognition.

Layout Analysis Module Models:

Model	Model Download Link	mAP(0.5) (%)	CPU Inference Time (ms) [Normal Mode / High-Performance Mode]	CPU Inference Time (ms) [Normal Mode / High-Performance Mode]	Model Size (M)	Description
PicoDet_layout_1x	Inference Model/Trained Model	86.8	9.03 / 3.10	25.82 / 20.70	7.4	An efficient layout area localization model trained on the PubLayNet dataset based on PicoDet-1x can locate five types of areas, including text, titles, tables, images, and lists.
PicoDet_layout_1x_table	Inference Model/Trained Model	95.7	8.02 / 3.09	23.70 / 20.41	7.4 M	An efficient layout area localization model trained on the PubLayNet dataset based on PicoDet-1x can locate one type of tables.
PicoDet-S_layout_3cls	Inference Model/Trained Model	87.1	8.99 / 2.22	16.11 / 8.73	4.8	An high-efficient layout area localization model trained on a self-constructed dataset based on PicoDet-S for scenarios such as Chinese and English papers, magazines, and research reports includes three categories: tables, images, and seals.
PicoDet-S_layout_17cls	Inference Model/Trained Model	70.3	9.11 / 2.12	15.42 / 9.12	4.8	A high-efficient layout area localization model trained on a self-constructed dataset based on PicoDet-S_layout_17cls for scenarios such as Chinese and English papers, magazines, and research reports includes 17 common layout categories, namely: paragraph titles, images, text, numbers, abstracts, content, chart titles, formulas, tables, table titles, references, document titles, footnotes, headers, algorithms, footers, and seals.
PicoDet-L_layout_3cls	Inference Model/Trained Model	89.3	13.05 / 4.50	41.30 / 41.30	22.6	An efficient layout area localization model trained on a self-constructed dataset based on PicoDet-L for scenarios such as Chinese and English papers, magazines, and research reports includes three categories: tables, images, and seals.
PicoDet-L_layout_17cls	Inference Model/Trained Model	79.9	13.50 / 4.69	43.32 / 43.32	22.6	A efficient layout area localization model trained on a self-constructed dataset based on PicoDet-L_layout_17cls for scenarios such as Chinese and English papers, magazines, and research reports includes 17 common layout categories, namely: paragraph titles, images, text, numbers, abstracts, content, chart titles, formulas, tables, table titles, references, document titles, footnotes, headers, algorithms, footers, and seals.
RT-DETR-H_layout_3cls	Inference Model/Trained Model	95.9	114.93 / 27.71	947.56 / 947.56	470.1	A high-precision layout area localization model trained on a self-constructed dataset based on RT-DETR-H for scenarios such as Chinese and English papers, magazines, and research reports includes three categories: tables, images, and seals.
RT-DETR-H_layout_17cls	Inference Model/Trained Model	92.6	115.29 / 104.09	995.27 / 995.27	470.2	A high-precision layout area localization model trained on a self-constructed dataset based on RT-DETR-H for scenarios such as Chinese and English papers, magazines, and research reports includes 17 common layout categories, namely: paragraph titles, images, text, numbers, abstracts, content, chart titles, formulas, tables, table titles, references, document titles, footnotes, headers, algorithms, footers, and seals.

Text Detection Module Models:

Model Name	Model Download Link	Detection Hmean (%)	CPU Inference Time (ms) [Normal Mode / High-Performance Mode]	CPU Inference Time (ms) [Normal Mode / High-Performance Mode]	Model Size (M)
PP-OCRv4_mobile_det	Inference Model/Trained Model	77.79	8.79 / 3.13	51.00 / 28.58	4.2 M
PP-OCRv4_server_det	Inference Model/Trained Model	82.69	83.34 / 80.91	442.58 / 442.58	100.1M

Test Environment Description:

Performance Test Environment
- Test Dataset:
- Document Image Orientation Classification Model: A self-built dataset using PaddleX, covering various scenarios such as ID cards and documents, containing 1000 images.
- Text Image Rectification Model: DocUNet.
- Layout Region Detection Model: A self-built layout analysis dataset using PaddleOCR, containing 10,000 images of common document types such as Chinese and English papers, magazines, and research reports.
- Table Structure Recognition Model: A self-built English table recognition dataset using PaddleX.
- Text Detection Model: A self-built Chinese dataset using PaddleOCR, covering multiple scenarios such as street scenes, web images, documents, and handwriting, with 500 images for detection.
- Chinese Recognition Model: A self-built Chinese dataset using PaddleOCR, covering multiple scenarios such as street scenes, web images, documents, and handwriting, with 11,000 images for text recognition.
- ch_SVTRv2_rec: Evaluation set A for "OCR End-to-End Recognition Task" in the PaddleOCR Algorithm Model Challenge.
- ch_RepSVTR_rec: Evaluation set B for "OCR End-to-End Recognition Task" in the PaddleOCR Algorithm Model Challenge.
- English Recognition Model: A self-built English dataset using PaddleX.
- Multilingual Recognition Model: A self-built multilingual dataset using PaddleX.
- 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
Regular 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.)

2. Quick Start

PaddleX's pre-trained model pipelines allow for quick experience of their effects. You can experience the effects of the General Image Classification pipeline online or locally using command line or Python.

2.1 Online Experience

You can experience online the effects of the General Table Recognition pipeline by using the demo images provided by the official. For example:

If you are satisfied with the pipeline's performance, you can directly integrate and deploy it. If not, you can also use your private data to fine-tune the models in the pipeline online.

2.2 Local Experience

Before using the General Table Recognition pipeline locally, ensure you have installed the PaddleX wheel package following the PaddleX Local Installation Guide.

2.1 Command Line Experience

Experience the effects of the table recognition pipeline with a single command:

Experience the image anomaly detection pipeline with a single command，Use the test file, and replace --input with the local path to perform prediction.

paddlex --pipeline table_recognition --input table_recognition.jpg --device gpu:0

Parameter Explanation:

--pipeline: The name of the pipeline, here it's the table recognition pipeline.
--input: The local path or URL of the input image to be processed.
--device: The GPU index to use (e.g., gpu:0 for the first GPU, gpu:1,2 for the 1st and 2nd GPUs). CPU can also be selected (--device cpu).

When executing the above command, the default table recognition pipeline configuration file is loaded. If you need to customize the configuration file, you can execute the following command to obtain it:

👉Click to expand

paddlex --get_pipeline_config table_recognition

After execution, the table recognition pipeline configuration file will be saved in the current directory. If you wish to customize the save location, you can execute the following command (assuming the custom save location is ./my_path):

paddlex --get_pipeline_config table_recognition --save_path ./my_path

After obtaining the pipeline configuration file, replace --pipeline with the configuration file save path to make the configuration file take effect. For example, if the configuration file save path is ./table_recognition.yaml, simply execute:

paddlex --pipeline ./table_recognition.yaml --input table_recognition.jpg --device gpu:0

Here, parameters like --model and --device do not need to be specified, as they will use the parameters in the configuration file. If they are still specified, the specified parameters will take precedence.

After running, the result is:

The visualized image not saved by default. You can customize the save path through --save_path, and then all results will be saved in the specified path.

2.2 Python Script Integration

A few lines of code are all you need to quickly perform inference with the pipeline. Taking the General Table Recognition pipeline as an example:

from paddlex import create_pipeline

pipeline = create_pipeline(pipeline="table_recognition")

output = pipeline.predict("table_recognition.jpg")
for res in output:
    res.print()  # Print the structured output of the prediction
    res.save_to_img("./output/")  # Save the results in img format
    res.save_to_xlsx("./output/")  # Save the results in Excel format
    res.save_to_html("./output/") # Save results in HTML format

The results are the same as those obtained through the command line.

In the above Python script, the following steps are executed:

（1）Instantiate the pipeline object using create_pipeline: Specific parameter descriptions are as follows:

Parameter	Description	Type	Default
`pipeline`	The name of the pipeline or the path to the pipeline configuration file. If it is the name of the pipeline, it must be supported by PaddleX.	`str`	None
`device`	The device for pipeline model inference. Supports: "gpu", "cpu".	`str`	`gpu`
`config`	Specific configuration information for the pipeline (if set simultaneously with `pipeline`, it has higher priority than `pipeline`, and the pipeline name must be consistent with `pipeline`).	`dict[str, Any]`	`None`
`use_hpip`	Whether to enable high-performance inference, only available if the pipeline supports it.	`bool`	`False`

（2）Invoke the predict method of the pipeline object for inference prediction: The predict method parameter is x, which is used to input data to be predicted, supporting multiple input methods, as shown in the following examples:

Parameter Type	Parameter Description
Python Var	Supports directly passing in Python variables, such as numpy.ndarray representing image data.
str	Supports passing in the path of the file to be predicted, such as the local path of an image file: `/root/data/img.jpg`.
str	Supports passing in the URL of the file to be predicted, such as the network URL of an image file: Example.
str	Supports passing in a local directory, which should contain files to be predicted, such as the local path: `/root/data/`.
dict	Supports passing in a dictionary type, where the key needs to correspond to a specific task, such as "img" for image classification tasks. The value of the dictionary supports the above types of data, for example: `{"img": "/root/data1"}`.
list	Supports passing in a list, where the list elements need to be of the above types of data, such as `[numpy.ndarray, numpy.ndarray], ["/root/data/img1.jpg", "/root/data/img2.jpg"], ["/root/data1", "/root/data2"], [{"img": "/root/data1"}, {"img": "/root/data2/img.jpg"}]`.

（3）Obtain the prediction results by calling the predict method: The predict method is a generator, so prediction results need to be obtained through iteration. The predict method predicts data in batches, so the prediction results are in the form of a list.

（4）Process the prediction results: The prediction result for each sample is of dict type and supports printing or saving to files, with the supported file types depending on the specific pipeline. For example:

Method	Description	Method Parameters
save_to_img	Save the results as an img format file	`- save_path`: str, the path to save the file. When it's a directory, the saved file name will be consistent with the input file type;
save_to_html	Save the results as an html format file	`- save_path`: str, the path to save the file. When it's a directory, the saved file name will be consistent with the input file type;
save_to_xlsx	Save the results as a spreadsheet format file	`- save_path`: str, the path to save the file. When it's a directory, the saved file name will be consistent with the input file type;

Where save_to_img can save visualization results (including OCR result images, layout analysis result images, table structure recognition result images), save_to_html can directly save the table as an html file (including text and table formatting), and save_to_xlsx can save the table as an Excel format file (including text and formatting).

If you have a configuration file, you can customize the configurations of the image anomaly detection pipeline by simply modifying the pipeline parameter in the create_pipeline method to the path of the pipeline configuration file.

For example, if your configuration file is saved at ./my_path/table_recognition.yaml, you only need to execute:

from paddlex import create_pipeline
pipeline = create_pipeline(pipeline="./my_path/table_recognition.yaml")
output = pipeline.predict("table_recognition.jpg")
for res in output:
    res.print()  # Print the structured output of prediction
    res.save_to_img("./output/")  # Save results in img format
    res.save_to_xlsx("./output/")  # Save results in Excel format
    res.save_to_html("./output/") # Save results in HTML format

3. Development Integration/Deployment

If the pipeline meets your requirements for inference speed and accuracy in production, you can proceed with development integration/deployment.

If you need to directly apply the pipeline in your Python project, refer to the example code in 2.2 Python Script Integration.

Additionally, PaddleX provides three other deployment methods, detailed as follows:

🚀 High-Performance Inference: In actual production environments, many applications have stringent standards for deployment strategy performance metrics (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins that aim to deeply optimize model inference and pre/post-processing for significant end-to-end process acceleration. For detailed high-performance inference procedures, refer to the PaddleX High-Performance Inference Guide.

☁️ Serving: Serving is a common deployment strategy in real-world production environments. By encapsulating inference functions into services, clients can access these services via network requests to obtain inference results. PaddleX supports various solutions for serving pipelines. For detailed pipeline serving procedures, please refer to the PaddleX Pipeline Serving Guide.

Below are the API reference and multi-language service invocation examples for the basic serving solution:

API Reference

For the main operations provided by the service:

The HTTP request method is POST.
The request body and response body are both JSON data (JSON objects).
When the request is processed successfully, the response status code is 200, and the attributes of the response body are as follows:

Name	Type	Meaning
`logId`	`string`	The UUID of the request.
`errorCode`	`integer`	Error code. Fixed as `0`.
`errorMsg`	`string`	Error message. Fixed as `"Success"`.
`result`	`object`	The result of the operation.

When the request is not processed successfully, the attributes of the response body are as follows:

Name	Type	Meaning
`logId`	`string`	The UUID of the request.
`errorCode`	`integer`	Error code. Same as the response status code.
`errorMsg`	`string`	Error message.

The main operations provided by the service are as follows:

infer

Locate and recognize tables in the image.

POST /table-recognition

The properties of the request body are as follows:

Name	Type	Meaning	Required
`file`	`string`	The URL of an image file or PDF file accessible by the server, or the Base64 encoding result of the content of the above file types. For PDF files exceeding 10 pages, only the content of the first 10 pages will be used.	Yes
`fileType`	`integer` \| `null`	The file type. `0` represents a PDF file, and `1` represents an image file. If this attribute is not present in the request body, the file type will be inferred based on the URL.	No
`useDocOrientationClassify`	`boolean` \| `null`	See the description of the `use_doc_orientation_classify` parameter in the `predict` method of the pipeline.	No
`useDocUnwarping`	`boolean` \| `null`	See the description of the `use_doc_unwarping` parameter in the `predict` method of the pipeline.	No
`useLayoutDetection`	`boolean` \| `null`	See the description of the `use_layout_detection` parameter in the `predict` method of the pipeline.	No
`useOcrModel`	`boolean` \| `null`	See the description of the `use_ocr_model` parameter in the `predict` method of the pipeline.	No
`layoutThreshold`	`number` \| `null`	See the description of the `layout_threshold` parameter in the `predict` method of the pipeline.	No
`layoutNms`	`boolean` \| `null`	See the description of the `layout_nms` parameter in the `predict` method of the pipeline.	No
`layoutUnclipRatio`	`number` \| `array` \| `null`	See the description of the `layout_unclip_ratio` parameter in the `predict` method of the pipeline.	No
`layoutMergeBboxesMode`	`string` \| `null`	See the description of the `layout_merge_bboxes_mode` parameter in the `predict` method of the pipeline.	No
`textDetLimitSideLen`	`integer` \| `null`	See the description of the `text_det_limit_side_len` parameter in the `predict` method of the pipeline.	No
`textDetLimitType`	`string` \| `null`	See the description of the `text_det_limit_type` parameter in the `predict` method of the pipeline.	No
`textDetThresh`	`number` \| `null`	See the description of the `text_det_thresh` parameter in the `predict` method of the pipeline.	No
`textDetBoxThresh`	`number` \| `null`	See the description of the `text_det_box_thresh` parameter in the `predict` method of the pipeline.	No
`textDetUnclipRatio`	`number` \| `null`	See the description of the `text_det_unclip_ratio` parameter in the `predict` method of the pipeline.	No
`textRecScoreThresh`	`number` \| `null`	See the description of the `text_rec_score_thresh` parameter in the `predict` method of the pipeline.	No

When the request is processed successfully, the result in the response body has the following attributes:

Name	Type	Description
`tableRecResults`	`object`	The table recognition result. The length of the array is 1 (for image input) or the smaller of the number of document pages and 10 (for PDF input). For PDF input, each element in the array represents the processing result of each page in the PDF file.
`dataInfo`	`object`	Information about the input data.

Each element in tableRecResults is an object with the following attributes:

Name	Type	Description
`prunedResult`	`object`	The simplified version of the `res` field in the JSON representation generated by the `predict` method of the production object, with the `input_path` field removed.
`outputImages`	`object` \| `null`	See the description of the `img` attribute in the result of the pipeline prediction. The images are in JPEG format and encoded in Base64.
`inputImage`	`string` \| `null`	The input image. The image is in JPEG format and encoded in Base64.

Multi-language service call example

Python

import base64
import requests

API_URL = "http://localhost:8080/table-recognition"
file_path = "./demo.jpg"

with open(file_path, "rb") as file:

file_bytes = file.read()
file_data = base64.b64encode(file_bytes).decode("ascii")


payload = {"file": file_data, "fileType": 1}

response = requests.post(API_URL, json=payload)

assert response.status_code == 200
result = response.json()["result"]
for i, res in enumerate(result["tableRecResults"]):

print(res["prunedResult"])
for img_name, img in res["outputImages"].items():
    img_path = f"{img_name}_{i}.jpg"
    with open(img_path, "wb") as f:
        f.write(base64.b64decode(img))
    print(f"Output image saved at {img_path}")

📱 Edge Deployment: Edge deployment is a method that places computing and data processing capabilities directly on user devices, allowing devices to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, refer to the PaddleX Edge Deployment Guide. Choose the appropriate deployment method for your model pipeline based on your needs, and proceed with subsequent AI application integration.

4. Custom Development

If the default model weights provided by the general table recognition pipeline do not meet your requirements for accuracy or speed in your specific scenario, you can try to further fine-tune the existing model using your own domain-specific or application-specific data to improve the recognition performance of the general table recognition pipeline in your scenario.

4.1 Model Fine-tuning

Since the general table recognition pipeline consists of four modules, unsatisfactory performance may stem from any of these modules.

Analyze images with poor recognition results and follow the rules below for analysis and model fine-tuning:

If the detected table structure is incorrect (e.g., row and column recognition errors, incorrect cell positions), the table structure recognition module may be insufficient. You need to refer to the Customization section in the Table Structure Recognition Module Development Tutorial and use your private dataset to fine-tune the table structure recognition model.
If the table area is incorrectly located within the overall layout, the layout detection module may be insufficient. You need to refer to the Customization section in the Layout Detection Module Development Tutorial and use your private dataset to fine-tune the layout detection model.
If many texts are undetected (i.e., text miss detection), the text detection model may be insufficient. You need to refer to the Customization section in the Text Detection Module Development Tutorial and use your private dataset to fine-tune the text detection model.
If many detected texts contain recognition errors (i.e., the recognized text content does not match the actual text content), the text recognition model requires further improvement. You need to refer to the Customization section.

4.2 Model Application

After fine-tuning your model with a private dataset, you will obtain local model weights files.

To use the fine-tuned model weights, simply modify the pipeline configuration file by replacing the local path of the fine-tuned model weights to the corresponding location in the configuration file:

......
 Pipeline:
  layout_model: PicoDet_layout_1x  # Can be modified to the local path of the fine-tuned model
  table_model: SLANet  # Can be modified to the local path of the fine-tuned model
  text_det_model: PP-OCRv4_mobile_det  # Can be modified to the local path of the fine-tuned model
  text_rec_model: PP-OCRv4_mobile_rec  # Can be modified to the local path of the fine-tuned model
  layout_batch_size: 1
  text_rec_batch_size: 1
  table_batch_size: 1
  device: "gpu:0"
......

Then, refer to the command line or Python script method in the local experience to load the modified pipeline configuration file.

5. Multi-Hardware Support

PaddleX supports various mainstream hardware devices such as NVIDIA GPU, Kunlun XPU, Ascend NPU, and Cambricon MLU. Simply modify the --device parameter to seamlessly switch between different hardware.

For example, if you use an NVIDIA GPU for table recognition pipeline inference, the Python command is:

paddlex --pipeline table_recognition --input table_recognition.jpg --device gpu:0

At this time, if you want to switch the hardware to Ascend NPU, simply modify --device in the Python command to npu:

paddlex --pipeline table_recognition --input table_recognition.jpg --device npu:0

If you want to use the general table recognition pipeline on more types of hardware, please refer to the PaddleX Multi-Hardware Usage Guide.

table_recognition.en.md 36 KB Verlauf Originalformat