Antiporn Recognition
Last Updated：2021-09-30
Feature Description
Antiporn recognition.
Request Parameters
No
Return Parameters
| Field | Type | Required? | Description |
|---|---|---|---|
| confidence_coefficient | string | Yes | Whether to confirm the result? It includes "Confirmed" and "Unconfirmed". |
| result_num | uint32 | Yes | Number of results returned, i.e., number of elements in the results array. |
| result | array(array(double)) | Yes | Results array. Each item corresponds to the results of a classification dimension. |
| conclusion | string | Yes | Final identification results of the image, which includes "pornographic", "sexy" and "normal". |
| log_id | uint64 | Yes | Request ID, random number, unique. |
Each item of the element contains the following fields:
| Field | Type | Required? | Description | Example |
|---|---|---|---|---|
| class_name | string | Yes | Classification results name | Antiporn |
| probability | double | Yes | Classification results confidence level | 0.89471650123596 |
Return Example
{
"result": [{
"probability": 0.000301,
"class_name": "Pornographic"
},
{
"probability": 0.000054,
"class_name":"Sexy"
},
{
"probability": 0.999645,
"class_name": "Normal"
}],
"conclusion": "normal",
"log_id": 848999404,
"confidence_coefficient": "certain",
"result_num": 3
}