Turning on Smart Tags
Smart Tags use Amazon Web Services Rekognition to identify objects, features, and details of images and creates relevant labels that are automatically attached to the asset.
Note: If you do not see the Smart Tags settings, please contact your Account manager to enable this feature for you.
To set up Smart Tags:
1) Navigate to the Settings and select the tab Configuration Options, followed by the sub-tab Smart Tags
2) Toggle the Smart Tags option to On
Images - Smart Tags
Click Recreate Smart Tags (this is will identify any images that were already uploaded and any new images) and Save.
Choose a number between 0-99 for the Min. Confidence Score for AWS Rekognition to follow. The Confidence Score is a number between 0 and 99 that indicates the probability that a predicted detection is correct. Canto does not return any tags with a Confidence Score lower than the specified value. The lower the score, the more (and potentially less relevant) Smart Tags will be returned.
Choose a number between 1-30 for the Maximum Tag amount. This is the maximum number of tags that you want Smart Tags to return. The returned tags will have the highest Confidence Scores of the detected details in the image.
Videos - Smart Tags
Similar to Smart Tags for Images you can control the Confidence Score and control the Maximum Tag amount for each video. The length of the video will affect the time it takes for the recognition software to process.
For video recognition, you will have a preset number of hours of content you can identify. You can view the number of hours you have and the number of hours you have used. The number of hours can be adjusted after reaching to your account manager. Your hour usage is combined with the Facial Recognition feature.
When using the Smart Tag feature for videos, you will need to manually identify video by selecting the desired video in the main library and click on the Generate Smart Tag icon. You will receive an email once this process is completed.
If you have questions on the technical components behind AWS Rekognition, check out their website.