The Likeness model classifies a video or image into different categories by assigning a confidence score for each class. The confidence scores indicate the likelihood of a given character being present in the image, and are independent of each other. For example, an image might contain both Sonic the hedgehog and Superman, and would be flagged as such by the respective classes.
{
"output": [
{
"time": 0,
"classes": [
{
"class": "superman",
"score": 0.9,
"parent_company": "Warner Bros.",
"category": "entertainment_media"
},
{
"class": "venom",
"score": 0.05,
"parent_company": "Disney",
"category": "entertainment_media"
},
{
"class": "mulan",
"score": 0.00,
"parent_company": "Disney",
"category": "entertainment_media"
},
{
"class": "wonder_woman",
"score": 0.88,
"parent_company": "Warner Bros.",
"category": "entertainment_media"
]
}
]
}| Name | Description |
|---|---|
| time | Timestamp in seconds of video or audio frame extracted from the original media. Always 0 for images |
| classes | List of objects for each output class that the API predicts. |
| class | Name of predicted class. |
| score | Confidence score of predicted class. |
| parent_company | Company that owns predicted class. |
| category | Likeness type of predicted class. |