PP-OCRv5 Service Deployment & API Usage Example:

PaddleOCR open-source project GitHub address, the code here is completely consistent with the open-source model.

1. Introduction to PP-OCRv5 Production Line

OCR (Optical Character Recognition) is a technology that converts text content in images into editable text. It is widely used in document digitization, information extraction, data processing, and other scenarios. OCR can recognize various types of text, including printed and handwritten characters, helping users efficiently obtain key information from images.

PP-OCRv5 is the latest generation text recognition solution in the PP-OCR series, designed for multi-scenario and multi-text-type recognition tasks. Compared to previous versions, PP-OCRv5 has achieved comprehensive upgrades in text type support and adaptability to various application scenarios. This solution can not only return the coordinates of text lines but also output the corresponding text content and its confidence score, effectively improving the accuracy and practicality of text detection and recognition. The features of this solution are as follows:

• Support for five major text types: Simplified Chinese, Chinese Pinyin, Traditional Chinese, English, and Japanese.
• Powerful multi-scenario adaptability: including complex Chinese-English handwritten text, vertical text, rare characters, and other challenging scenarios.
• On internal multi-scenario complex evaluation sets, PP-OCRv5 achieves a 13 percentage point improvement in end-to-end recognition accuracy compared to the previous generation, PP-OCRv4.

The overall workflow of the PP-OCRv5 production line is shown below:

2. API Description

This applies to scenarios where parsing tasks are created via API. Users must first apply for a Token. Note:

• Each user has a daily limit of 3000 pages per model for parsing. Further parsing requests will return a 429 error.
• There is no limit on the number of pages or file size for a single file, but if large files cause resource constraints, the service may time out and return a 503 error.

3. Service Call Example (python)

# Please make sure the requests library is installed
# pip install requests
import os
import base64
import requests

# Please visit https://aistudio.baidu.com/paddleocr/task to obtain the API_URL and TOKEN in the API call example.
API_URL = "<your url>"
TOKEN = "<access token>"

file_path = "<local file path>"
input_filename = os.path.splitext(os.path.basename(file_path))[0]

with open(file_path, "rb") as file:
    file_bytes = file.read()
    file_data = base64.b64encode(file_bytes).decode("ascii")

headers = {
    "Authorization": f"token {TOKEN}",
    "Content-Type": "application/json"
}

required_payload = {
    "file": file_data,
    "fileType": <file type>,  # For PDF documents, set `fileType` to 0; for images, set `fileType` to 1
}

optional_payload = {
    "useDocOrientationClassify": False,
    "useDocUnwarping": False,
    "useTextlineOrientation": False,
}

payload = {**required_payload, **optional_payload}

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

assert response.status_code == 200
result = response.json()["result"]

os.makedirs("output", exist_ok=True)

for i, res in enumerate(result["ocrResults"]):
    print(res["prunedResult"])
    image_url = res["ocrImage"]
    img_response = requests.get(image_url)
    if img_response.status_code == 200:
        # Save image to local
        filename = f"output/{input_filename}_{i}.jpg"
        with open(filename, "wb") as f:
            f.write(img_response.content)
        print(f"Image saved to: {filename}")
    else:
        print(f"Failed to download image, status code: {img_response.status_code}")

Main operations provided by the service:

• The HTTP request method is POST.
• Both the request body and response body are JSON data (JSON objects).
• When the request is processed successfully, the response status code is200. The response body has the following properties:

• When the request fails, the response body has the following properties:

The main operation provided by the service is as follows:

• infer

Obtain OCR results for images.

POST /ocr

4. Request Parameter Description

Serving:
  extra:
    max_num_input_imgs: null

Serving:
  visualize: False

• When the request is processed successfully, the result field in the response body has the following properties:

Each element in ocrResults is an object with the following properties:

5. Error Code Description

Note: If you encounter any issues during use, please feel free to submit feedback in the issue section.