The facial recognition feature in Canto allows the user to choose a Confidence Level to recognize the faces at.  The higher the confidence level, the more accurate the feature will be, but fewer faces may be identified.  The lower the confidence level, the less accurate the feature will be, but more faces will be identified.

Users can adjust the confidence level depending on the size of their Canto library.

The Reidentify Faces feature will re-analyze your entire Canto library to recognize faces.  This is recommended to alter the number of faces and the accuracy of faces recognized.  

Note: this feature removes the names entered for all faces.

The button will remain Grey while the software is identifying faces, and will reappear as normal once the process has completed.  Admins will also receive an Email Notification once the process is over.

To Remove Faces that you have identified in your Canto Library, uncheck the box "Setup Facial Recognition to Identify People from and Image."  Then, select "Remove Faces."  This feature will completely remove the faces previously identified.

If you were  to run into the following error message, you will need to upload a reference picture before using the Facial Recognition:

We recommend that you upload an image that contains a full face and shoulders of the person. It is important to upload this first picture as a reference picture to help better identify pictures. Especially, for group photos. See below for sample images:

Here are some other items to consider when selecting a reference image. More information on the functionality of our Facial Recognition system can be found here as well. 

Metric  Fail Condition


Confidence c<98 A face must be used.
(brightness & sharpness)  
s<60 || b<30Use images that are bright and sharp.
(pitch, yaw && roll)
p<-30 || p>45
|| y<-45 || y>45
Use an image with a face that is within the recommended range of angles. The pitch should be less than 30 degrees face down and less than 45 degrees face up. The yaw should be less than 45 degrees in either direction. There is no restriction on the roll.
Eyes Open e>90 Use an image of a face with both eyes open and visible
Bounding Box
(left, top, width & height, all in ratio)
l<0.01 || t<0.01
|| l + w>0.99 || t + h>0.99
The image should contain the full head and shoulders of the person. It should not be cropped to the face bounding box.
w*h<0.01Use an image of a face that occupies a large proportion of the image. Images with a face that occupies a larger portion of the image, are matched with greater accuracy.
(Happy: h; Calm: c; Other emotions)

{emotion not happy not calm} >90 || h<10 && c<10 

Use images of faces with neutral facial expressions with mouth closed with little to no smile for applications that require high precision.
width & height in pixel
Width x Height <4000 Ensure that images are sufficiently large enough with respect to resolution.