Yes, we have support for detecting, grouping and labelling faces. This means that if you label some of your friends, others will get automatically labelled so you can quickly find other photos of them.
These are the main steps of the process for each photo:
- Detect face positions and sizes in photos that are imported.
- Crop, transform and align face to correct for people positioning their heads differently.
- Compute embedding “fingerprint” for each face image.
- Build a Nearest Neighbours search index to quickly compute distance between face embeddings. If two faces are close enough together, tag them as being the same person.
- Provide user interface so a human can label, accept or reject the face groups that were found.
More details are given in our announcement blog post and Image Analysis documentation.
