Face attributes
Locate faces and return structured information about image quality, head pose, and estimated visible attributes.
/face/attributesmultipart/form-dataRequest
Send an image containing one or more faces as the image multipart form-data field.
| Form field | Type | Required |
|---|---|---|
image | Image file | Yes |
Set RAPIDAPI_KEY and RAPIDAPI_HOST to the values from this API’s listing. The following example uses a POSIX shell. Replace the local filenames with your images.
curl --request POST \
--url "https://$RAPIDAPI_HOST/face/attributes" \
--header "X-RapidAPI-Key: $RAPIDAPI_KEY" \
--header "X-RapidAPI-Host: $RAPIDAPI_HOST" \
--form 'image=@./image.jpg'Response example
{
"faceCount": 1,
"faces": [
{
"boundingBox": {
"left": 0.21,
"top": 0.18,
"width": 0.57,
"height": 0.79
},
"detectionConfidence": 99.99,
"ageLow": 22,
"ageHigh": 28,
"gender": "Female",
"genderConfidence": 99.9,
"smile": true,
"eyeglasses": false,
"sunglasses": false,
"beard": false,
"mustache": false,
"eyesOpen": true,
"mouthOpen": true,
"emotions": [
{
"type": "HAPPY",
"confidence": 100
}
],
"sharpness": 94.1,
"brightness": 88.3,
"pitch": -3.2,
"roll": 1.1,
"yaw": 5.4
}
]
}Core response fields
This guide focuses on the fields used in application workflows. Responses may include additional metadata; consult the API listing for the full schema.
| Field | Type | Meaning |
|---|---|---|
faceCount | number | Number of detected faces. |
faces[].boundingBox | object | Face location as ratios of image width and height, measured from the top-left. |
faces[].detectionConfidence | number | Face detection confidence. |
faces[].sharpness / brightness | number | Image quality measurements for the face region, from 0 to 100. |
faces[].pitch / roll / yaw | number | Head pose angles in degrees. |
faces[].ageLow / ageHigh | number | An estimated age range, not a verified age. |
faces[].gender / emotions | estimates | Model predictions with confidence scores, not verified personal characteristics or internal emotional states. |
faces[].genderConfidence | number | Confidence in the gender prediction, from 0 to 100. |
faces[].smile / eyeglasses / sunglasses | boolean | Detected visible traits. |
faces[].beard / mustache | boolean | Detected facial-hair traits. |
faces[].eyesOpen / mouthOpen | boolean | Detected eye and mouth state. |
faces[].emotions[] | array | Predicted emotion labels with type and confidence, most-confident first. |
Use image-quality and pose signals to guide better image capture. Estimated attributes should not be treated as verified facts about a person.
Limits and integration notes
- The published image upload limit is 20 MB. Resize files that exceed the limit before sending them.
- Keep keys server-side and use the correct host for the API. See authentication.
- Handle bad inputs and temporary failures using the error guide.
- Vision input images are processed in-request without storage by Tigrate. See data handling.
Based on the published RapidAPI reference, checked September 2026. Consult the listing for the latest full schema, optional parameters, and plan limits.