The core task of structure analysis is to parse and segment the content of input document images. By identifying different elements in the image (such as text, charts, images, etc.), they are classified into predefined categories (e.g., pure text area, title area, table area, image area, list area, etc.), and the position and size of these regions in the document are determined.
## II. Supported Model List
*<b>The layout detection model includes 20 common categories: document title, paragraph title, text, page number, abstract, table, references, footnotes, header, footer, algorithm, formula, formula number, image, table, seal, figure_table title, chart, and sidebar text and lists of references</b>
<table>
<thead>
<tr>
<th>Model</th><th>Model Download Link</th>
<th>mAP(0.5) (%)</th>
<th>GPU Inference Time (ms)<br/>[Normal Mode / High-Performance Mode]</th>
<th>CPU Inference Time (ms)<br/>[Normal Mode / High-Performance Mode]</th>
<td>A higher-precision layout area localization model trained on a self-built dataset containing Chinese and English papers, PPT, multi-layout magazines, contracts, books, exams, ancient books and research reports using RT-DETR-L</td>
</tr>
<tr>
</tbody>
</table>
*<b>The layout detection model includes 1 category: Block:</b>
<table>
<thead>
<tr>
<th>Model</th><th>Model Download Link</th>
<th>mAP(0.5) (%)</th>
<th>GPU Inference Time (ms)<br/>[Normal Mode / High-Performance Mode]</th>
<th>CPU Inference Time (ms)<br/>[Normal Mode / High-Performance Mode]</th>
<td>A layout block localization model trained on a self-built dataset containing Chinese and English papers, PPT, multi-layout magazines, contracts, books, exams, ancient books and research reports using RT-DETR-L</td>
</tr>
<tr>
</tbody>
</table>
*<b>The layout detection model includes 23 common categories: document title, paragraph title, text, page number, abstract, table of contents, references, footnotes, header, footer, algorithm, formula, formula number, image, figure caption, table, table caption, seal, figure title, figure, header image, footer image, and sidebar text</b>
<table>
<thead>
<tr>
<th>Model</th><th>Model Download Link</th>
<th>mAP(0.5) (%)</th>
<th>GPU Inference Time (ms)<br/>[Normal Mode / High-Performance Mode]</th>
<th>CPU Inference Time (ms)<br/>[Normal Mode / High-Performance Mode]</th>
<td>A high-precision layout area localization model trained on a self-built dataset containing Chinese and English papers, magazines, contracts, books, exams, and research reports using RT-DETR-L.</td>
<td>A layout area localization model with balanced precision and efficiency, trained on a self-built dataset containing Chinese and English papers, magazines, contracts, books, exams, and research reports using PicoDet-L.</td>
<td>A high-efficiency layout area localization model trained on a self-built dataset containing Chinese and English papers, magazines, contracts, books, exams, and research reports using PicoDet-S.</td>
</tr>
</tbody>
</table>
> ❗ The above list includes the <b>4 core models</b> that are key supported by the text recognition module. The module actually supports a total of <b>12 full models</b>, including several predefined models with different categories. The complete model list is as follows:
<details><summary> 👉 Details of Model List</summary>
*<b>Table Layout Detection Model</b>
<table>
<thead>
<tr>
<th>Model</th><th>Model Download Link</th>
<th>mAP(0.5) (%)</th>
<th>GPU Inference Time (ms)<br/>[Normal Mode / High-Performance Mode]</th>
<th>CPU Inference Time (ms)<br/>[Normal Mode / High-Performance Mode]</th>
<td>A high-efficiency layout area localization model trained on a self-built dataset of Chinese and English papers, magazines, and research reports using PicoDet-S.</td>
<td>A balanced efficiency and precision layout area localization model trained on a self-built dataset of Chinese and English papers, magazines, and research reports using PicoDet-L.</td>
<td>A high-precision layout area localization model trained on a self-built dataset of Chinese and English papers, magazines, and research reports using RT-DETR-H.</td>
</tr>
</tbody></table>
*<b>5-Class English Document Area Detection Model, including Text, Title, Table, Image, and List</b>
<table>
<thead>
<tr>
<th>Model</th><th>Model Download Link</th>
<th>mAP(0.5) (%)</th>
<th>GPU Inference Time (ms)<br/>[Normal Mode / High-Performance Mode]</th>
<th>CPU Inference Time (ms)<br/>[Normal Mode / High-Performance Mode]</th>
<td>A high-efficiency layout area localization model trained on a self-built dataset of Chinese and English papers, magazines, and research reports using PicoDet-S.</td>
<td>A balanced efficiency and precision layout area localization model trained on a self-built dataset of Chinese and English papers, magazines, and research reports using PicoDet-L.</td>
<td>A high-precision layout area localization model trained on a self-built dataset of Chinese and English papers, magazines, and research reports using RT-DETR-H.</td>
</tr>
</tbody>
</table>
<strong>Test Environment Description:</strong>
<ul>
<li><b>Performance Test Environment</b>
<ul>
<li><strong>Test Dataset：</strong>
<ul>
<li>20 types of layout detection models: PaddleOCR's self built layout area detection dataset, including Chinese and English papers, magazines, newspapers, research papers PPT、 1300 images of document types such as test papers and textbooks. </li>
<li>Type 1 version face region detection model: PaddleOCR's self built version face region detection dataset, including Chinese and English papers, magazines, newspapers, research reports PPT、 1000 document type images such as test papers and textbooks. </li>
<li>23 categories Layout Detection Model: A self-built layout area detection dataset by PaddleOCR, containing 500 common document type images such as Chinese and English papers, magazines, contracts, books, exam papers, and research reports.</li>
<li>Table Layout Detection Model: A self-built table area detection dataset by PaddleOCR, including 7,835 Chinese and English paper document type images with tables.</li>
<li> 3-Class Layout Detection Model: A self-built layout area detection dataset by PaddleOCR, comprising 1,154 common document type images such as Chinese and English papers, magazines, and research reports.</li>
<li>5-Class English Document Area Detection Model: The evaluation dataset of <ahref="https://developer.ibm.com/exchanges/data/all/publaynet">PubLayNet</a>, containing 11,245 images of English documents.</li>
<li>17-Class Area Detection Model: A self-built layout area detection dataset by PaddleOCR, including 892 common document type images such as Chinese and English papers, magazines, and research reports.</li>
> ❗ Before quick integration, please install the PaddleOCR wheel package. For detailed instructions, refer to [PaddleOCR Local Installation Tutorial](../installation.en.md)。
You can also integrate the model inference from the layout area detection module into your project. Before running the following code, please download [Example Image](https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/layout.jpg) Go to the local area.
```python
from paddleocr import LayoutDetection
model = LayoutDetection(model_name="PP-DocLayout_plus-L")
-`input_path`: The path to the input image for prediction.
-`page_index`: If the input is a PDF file, it indicates which page of the PDF it is; otherwise, it is `None`.
-`boxes`: Information about the predicted bounding boxes, a list of dictionaries. Each dictionary represents a detected object and contains the following information:
-`cls_id`: Class ID, an integer.
-`label`: Class label, a string.
-`score`: Confidence score of the bounding box, a float.
-`coordinate`: Coordinates of the bounding box, a list of floats in the format <code>[xmin, ymin, xmax, ymax]</code>.
<td>Whether to use the high performance inference.</td>
<td><code>bool</code></td>
<td><code>False</code></td>
</tr>
<tr>
<td><code>use_tensorrt</code></td>
<td>Whether to use the Paddle Inference TensorRT subgraph engine.</td>
<td><code>bool</code></td>
<td><code>False</code></td>
</tr>
<tr>
<td><code>min_subgraph_size</code></td>
<td>Minimum subgraph size for TensorRT when using the Paddle Inference TensorRT subgraph engine.</td>
<td><code>int</code></td>
<td><code>3</code></td>
</tr>
<tr>
<td><code>precision</code></td>
<td>Precision for TensorRT when using the Paddle Inference TensorRT subgraph engine.<br/><b>Options:</b><code>fp32</code>, <code>fp16</code>, etc.</td>
<td>Whether to use NMS post-processing to filter overlapping boxes; if not specified, the default PaddleOCR official model configuration will be used<br/><b>Examples:</b>
<td>Scaling factor for the side length of the detection box; if not specified, the default PaddleX official model configuration will be used<br/><b>Examples:</b>
<td>Bounding box merge mode for model output; ; if not specified, the default PaddleOCR official model configuration will be used.<br/><b>Examples:</b>
* Note that `model_name` must be specified. After specifying `model_name`, the default PaddleX built-in model parameters will be used. If `model_dir` is specified, the user-defined model will be used.
* The `predict()` method of the target detection model is called for inference prediction. The parameters of the `predict()` method are `input`, `batch_size`, and `threshold`, which are explained as follows:
- Local image or PDF file path: <code>/root/data/img.jpg</code>;
-<b>URL</b> of image or PDF file: e.g., <ahref="https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/img_rot180_demo.jpg">example</a>;
-<b>Local directory</b>: directory containing images for prediction, e.g., <code>/root/data/</code> (Note: directories containing PDF files are not supported; PDFs must be specified by exact file path)</li>
<li><b>List</b>: Elements must be of the above types, e.g., <code>[numpy.ndarray, numpy.ndarray]</code>, <code>["/root/data/img1.jpg", "/root/data/img2.jpg"]</code>, <code>["/root/data1", "/root/data2"]</code></li>
<li><b>float</b>: e.g., 0.2, filters out all boxes with scores below 0.2</li>
<li><b>dict</b>: keys are <code>int</code> representing <code>cls_id</code>, and values are <code>float</code> thresholds. For example, <code>{0: 0.45, 2: 0.48, 7: 0.4}</code> applies thresholds of 0.45 to class 0, 0.48 to class 2, and 0.4 to class 7</li>
<li><b>None</b>: if not specified, defaults to 0.5</li>
<li><b>bool</b>: True/False, whether to apply NMS to filter overlapping detection boxes</li>
<li><b>None</b>: if not specified, uses the <code>layout_nms</code> value from <code>creat_model</code>; if that is also not set, NMS will not be used by default</li>
<li><b>float</b>:a positive float number, e.g., 1.1, means expanding the width and height of the detection box by 1.1 times while keeping the center unchanged</li>
<li><b>list</b>: e.g., [1.2, 1.5], means expanding the width by 1.2 times and the height by 1.5 times while keeping the center unchanged</li>
<li><b>dict</b>: keys are <code>int</code> representing <code>cls_id</code>, values are <code>tuple</code>, e.g., <code>{0: (1.1, 2.0)}</code> means cls_id 0 expanding the width by 1.1 times and the height by 2.0 times while keeping the center unchanged</li>
<li><b>None</b>: if not specified, defaults to 1.0</li>
<li><b>large</b>: keeps only the largest outer box when overlapping/contained boxes exist</li>
<li><b>small</b>: keeps only the smallest inner box when overlapping/contained boxes exist</li>
<li><b>union</b>: no filtering, keeps all overlapping boxes</li>
<li><b>dict</b>: keys are <code>int</code><code>cls_id</code>, values are <code>str</code>, e.g., <code>{0: "large", 2: "small"}</code> applies different merge modes to different classes</li>
<li><b>None</b>: if not specified, defaults to <code>union</code></li>
<p><sup>＊</sup> If <code>None</code> is passed to <code>predict()</code>, the value set during model instantiation (<code>__init__</code>) will be used; if it was also <code>None</code> there, the framework defaults are applied:<br>
* Process the prediction results, with each sample's prediction result being the corresponding Result object, and supporting operations such as printing, saving as an image, and saving as a 'json' file:
<table>
<thead>
<tr>
<th>Method</th>
<th>Method Description</th>
<th>Parameters</th>
<th>Parameter type</th>
<th>Parameter Description</th>
<th>Default value</th>
</tr>
</thead>
<tr>
<tdrowspan="3"><code>print()</code></td>
<tdrowspan="3">Print the result to the terminal</td>
<td><code>format_json</code></td>
<td><code>bool</code></td>
<td>Do you want to use <code>JSON</code> indentation formatting for the output content</td>
<td><code>True</code></td>
</tr>
<tr>
<td><code>indent</code></td>
<td><code>int</code></td>
<td>Specify the indentation level to enhance the readability of the <code>JSON</code> data output, only valid when <code>format_json</code> is <code>True</code></td>
<td>4</td>
</tr>
<tr>
<td><code>ensure_ascii</code></td>
<td><code>bool</code></td>
<td>Control whether to escape non ASCII characters to Unicode characters. When set to <code>True</code>, all non ASCII </code>characters will be escaped; <code>False</code> preserves the original characters and is only valid when <code>format_json</code> is <code>True</code></td>
<td><code>False</code></td>
</tr>
<tr>
<tdrowspan="3"><code>save_to_json()</code></td>
<tdrowspan="3">Save the result as a JSON format file</td>
<td><code>save_path</code></td>
<td><code>str</code></td>
<td>The saved file path, when it is a directory, the name of the saved file is consistent with the name of the input file type</td>
<td>None</td>
</tr>
<tr>
<td><code>indent</code></td>
<td><code>int</code></td>
<td>Specify the indentation level to enhance the readability of the <code>JSON</code> data output, only valid when <code>format_json</code> is <code>True</code></td>
<td>4</td>
</tr>
<tr>
<td><code>ensure_ascii</code></td>
<td><code>bool</code></td>
<td>Control whether to escape non ASCII characters to Unicode characters. When set to <code>True</code>, all non <code>ASCII</code> characters will be escaped; <code>False</code> preserves the original characters and is only valid when<code>format_json</code> is <code>True</code></td>
<td><code>False</code></td>
</tr>
<tr>
<td><code>save_to_img()</code></td>
<td>Save the results as an image format file</td>
<td><code>save_path</code></td>
<td><code>str</code></td>
<td>The saved file path, when it is a directory, the name of the saved file is consistent with the name of the input file type</td>
<td>None</td>
</tr>
</table>
* Additionally, it also supports obtaining the visualized image with results and the prediction results via attributes, as follows:
<table>
<thead>
<tr>
<th>Attribute</th>
<th>Description</th>
</tr>
</thead>
<tr>
<tdrowspan="1"><code>json</code></td>
<tdrowspan="1">Get the prediction result in <code>json</code> format</td>
</tr>
<tr>
<tdrowspan="1"><code>img</code></td>
<tdrowspan="1">Get the visualized image in <code>dict</code> format</td>
Since PaddleOCR does not directly provide training for the layout detection module, if you need to train the layout area detection model, you can refer to [PaddleX Layout Detection Module Secondary Development](https://paddlepaddle.github.io/PaddleX/latest/en/module_usage/tutorials/ocr_modules/layout_detection.html#iv-custom-development)Partially conduct training. The trained model can be seamlessly integrated into PaddleOCR's API for inference.
