Facial attribute detection

Prerequisites

Before you begin, ensure that you have:

• Python dependencies installed. See Installation for the required Python version. Using a different version causes operation calls to fail.

• The Extension.Uploader utility class downloaded and imported into your project (required for local file uploads only)

Usage notes

• Images are the only supported input type. Video and audio are not supported.

• Use the Content Moderation API endpoints when calling this SDK. See Endpoints.

• The API can detect the following facial attributes: face blur, angle, position, smile intensity, and whether the person is wearing glasses, a mask, a hat, has a beard, bangs, or specific hair types. For full parameter definitions and response schema, see the API operation for facial attribute detection.

• Reuse the instantiated AcsClient across requests to improve performance and avoid repeated connection overhead.

• Create a new DetectFaceRequest object for each request. Request objects cannot be reused.

Submit a face image URL

# coding=utf-8
import os
import json
from aliyunsdkcore import client
from aliyunsdkcore.profile import region_provider
from aliyunsdkgreen.request.v20180509 import DetectFaceRequest

# Initialize the client — reuse this instance across requests
# Load credentials from environment variables to avoid hardcoding sensitive values
clt = client.AcsClient(
    os.environ.get('ALIBABA_CLOUD_ACCESS_KEY_ID'),      # AccessKey ID
    os.environ.get('ALIBABA_CLOUD_ACCESS_KEY_SECRET'),  # AccessKey secret
    'cn-shanghai'
)
region_provider.modify_point('Green', 'cn-shanghai', 'green.cn-shanghai.aliyuncs.com')

# Create a new request object for each detection call
request = DetectFaceRequest.DetectFaceRequest()
request.set_accept_format('JSON')
request.set_content(json.dumps({"url": "http://example.com/xxx.jpg"}))

response = clt.do_action_with_exception(request)
print(response)
result = json.loads(response)

Submit a local file

To submit a local image file, use ClientUploader to upload the file and retrieve a temporary URL, then pass that URL to the detection request.

# coding=utf-8
import os
import json
from aliyunsdkcore import client
from aliyunsdkcore.profile import region_provider
from aliyunsdkgreen.request.v20180509 import DetectFaceRequest
from aliyunsdkgreenextension.request.extension import ClientUploader

# Initialize the client — reuse this instance across requests
# Load credentials from environment variables to avoid hardcoding sensitive values
clt = client.AcsClient(
    os.environ.get('ALIBABA_CLOUD_ACCESS_KEY_ID'),      # AccessKey ID
    os.environ.get('ALIBABA_CLOUD_ACCESS_KEY_SECRET'),  # AccessKey secret
    'cn-shanghai'
)
region_provider.modify_point('Green', 'cn-shanghai', 'green.cn-shanghai.aliyuncs.com')

# Upload the local file and get a temporary URL
clientUploader = ClientUploader.getImageClientUploader(clt)
url = clientUploader.uploadFile("/path/to/image.jpg")

# Create a new request object for each detection call
request = DetectFaceRequest.DetectFaceRequest()
request.set_accept_format('JSON')
request.set_content(json.dumps({"url": url}))

response = clt.do_action_with_exception(request)
print(response)
result = json.loads(response)

Replace /path/to/image.jpg with the absolute path to your image file.

What's next

• API operation for facial attribute detection — full parameter reference and response schema

• Endpoints — select the endpoint for your region