AddFaceImages
Adds training images to a face.
Type: synchronous
Parameter | Description | Required |
---|---|---|
database
|
The name of the database that contains the face. | Yes |
identifier
|
The identifier of the face that you want to add training images to. | Yes |
imagedata
|
The training images to add. Send files to Media Server using a multipart/form-data HTTP POST request. | Set this or imagepath |
imagelabels
|
A comma-separated list of labels to identify the images that you are adding (maximum 254 bytes for each label). Every image added to the same face must have a unique label, so the number of labels must match the number of images provided using either imagedata or imagepath . If you do not set this parameter, Media Server generates labels automatically. |
No |
imagepath
|
A comma-separated list of paths to the training images to add. The paths must be absolute, or relative to the Media Server executable file. To strengthen security, Media Server can be configured to read files only from specified directories. For information about the directories that Media Server is permitted to read from, see the parameter AllowedInputDirectories. |
Set this or imagedata |
Example
The following example adds training images to a face by specifying the paths of the images using the imagepath
parameter:
/action=AddFaceImages&database=politicians &identifier=6600dc0f9dd72d0cb55589e8f1d28b62 &imagepath=face1.jpg,face2.jpg &imagelabels=expression_smiling,expression_neutral
Alternatively, you can add training images by sending the image data, for example:
curl http://localhost:14000/action=AddFaceImages -F database=politicians -F identifier=6600dc0f9dd72d0cb55589e8f1d28b62 -F imagedata=@face1.jpg,face2.jpg -F imagelabels=expression_smiling,expression_neutral
Response
The response returns the labels assigned to the training images:
<autnresponse> <action>ADDFACEIMAGES</action> <response>SUCCESS</response> <responsedata> <images> <image> <index>1</index> <label>expression_smiling</label> </image> <image> <index>2</index> <label>expression_neutral</label> </image> </images> </responsedata> </autnresponse>
See Also
After adding training images for a face, you can train Media Server to recognize the face by running the action BuildFace.