This topic describes how to use Content Moderation SDK for Python to perform optical character recognition (OCR). This way, you can recognize text in images.


  • Python dependencies are installed. For more information, see Installation.
    Note You must use the required Python version described in the Installation topic to install the dependencies. Otherwise, subsequent operation calls fail.
  • The Extension.Uploader utility class is downloaded and imported into your project if you want to submit a local image or a binary image stream for image moderation.

Submit synchronous OCR tasks

Interface Description Supported region
ImageSyncScanRequest Submits synchronous OCR tasks to recognize text in images. Set the scenes parameter to ocr.
  • cn-shanghai: China (Shanghai)
  • cn-beijing: China (Beijing)
  • cn-shenzhen: China (Shenzhen)
  • ap-southeast-1: Singapore (Singapore)
  • ap-southeast-5: Indonesia (Jakarta)
Sample code
# The following code provides an example on how to use ImageSyncScanRequest to submit synchronous OCR tasks and obtain the moderation results in real time. 
from aliyunsdkcore import client
from aliyunsdkgreen.request.v20180509 import ImageSyncScanRequest
from aliyunsdkgreen.request.extension import HttpContentHelper
import json
import uuid

# Use the AccessKey pair of your Alibaba Cloud account. 
clt = client.AcsClient("yourAccessKeyId", "yourAccessKeySecret","cn-shanghai")
# The request object cannot be reused. You must create a request object for each request. 
request = ImageSyncScanRequest.ImageSyncScanRequest()
task = {"dataId": str(uuid.uuid1()),

# Create one task for each image to be moderated. 
# If you moderate multiple images in a request, the total response time that the server spends on processing the request starts from when the request is initiated to when the last image is moderated. 
# The average response time of moderating multiple images in a request is longer than that of moderating a single image. The more images you submit at a time, the higher the probability that the average response time will be extended. 
# In this example, a single image is moderated. If you need to moderate multiple images at a time, create one task for each image to be moderated. 
# The OCR expense equals the product of the number of images moderated and the moderation unit price. 
request.set_content(HttpContentHelper.toValue({"tasks": [task],
                                               "scenes": ["ocr"]
response = clt.do_action_with_exception(request)
result = json.loads(response)
if 200 == result["code"]:
    taskResults = result["data"]
    for taskResult in taskResults:
        if (200 == taskResult["code"]):
            sceneResults = taskResult["results"]