How the test works
The test runs two face comparisons: your face against one parent's, then your face against the other's. Each comparison gives a similarity score from 0 to 1, where a higher score means the two faces have more in common. The parent with the higher score is the one your face is closer to in these photos.
It is the same comparison the SightRadar API runs. The three photos are processed in memory and discarded once the two scores are worked out.
Reading the result
- More like one parent: one score is at least 0.05 higher than the other.
- Too close to call: the two scores are within 0.05 of each other. The same faces can move that much from one photo to the next, so a smaller gap is not a result.
- Not much like either: both scores are under 0.15. Clearer photos taken at a similar age may give a different answer.
Each bar also shows the line the API uses to call two photos the same person. A child and a parent are different people, so their scores normally sit under that line.
Getting a fair result
- Match the ages. A photo of each parent at about your age compares better than one taken decades later.
- Match the photos. Front-facing, similar light, similar expression. One smiling photo and one stern one tilts the result.
- One face per photo. When a photo has several faces, the largest, most confident one is used.
- Young children score lower. A small child's face is still changing shape, so it compares less steadily with an adult's.
The two slots take any two people, so the same test works for grandparents, siblings or friends. For a plain two-person comparison, use the look-alike test.
What it can't tell you
The result describes how alike the faces look in three particular photos. It says nothing about family ties and is not a DNA test. Upload your own photo and photos of family members who are happy to be compared; for a child's photo, a parent or guardian should be the one uploading it.
The same comparison in the API
Each of the two checks is one call to POST /v1/compare, the SightRadar equivalent of AWS Rekognition CompareFaces. On the API a comparison costs 186 credits (93 per image). See the compare endpoint reference.
Frequently asked questions
- How does the test decide which parent I look like?
- It runs two comparisons: your face against one parent's, then against the other's. Each gives a similarity score from 0 to 1. The higher score is the closer match. When the two scores are within 0.05 of each other the tool calls it too close to call, because a different pair of photos could tip it either way.
- Does it work for babies and young children?
- It runs, but expect lower and less steady scores. A young child's face is still changing shape, so it compares less reliably with an adult's. Photos taken at a similar age give the fairest comparison.
- Which photos give the fairest result?
- Clear, front-facing photos with one face each. Age matters most: a photo of a parent at about your age compares better than one taken decades later. Try to match the angle and the expression too, and skip sunglasses and heavy filters.
- Can I compare with grandparents, siblings or anyone else?
- Yes. The two slots take any two people: a grandparent and a parent, two siblings, two friends. The tool only compares the faces in the photos you give it.
- Does the result prove who I take after?
- No. It measures how alike the faces look in three particular photos. It says nothing about family ties and it is not a DNA test. Run it with different photos and the scores will move a little.
- Are my photos stored?
- No. The photos are processed in memory to work out the two scores and then discarded. No photo, face crop or faceprint is saved, and nothing is used to train models.
- Whose photos can I upload?
- Your own, and photos of family members who are happy to be compared. For a child's photo, a parent or guardian should be the one uploading it.
- Is the test free?
- Yes. There is no sign-up and no card. A fair-use limit per visitor keeps the tool fast for everyone; if you reach it, the tool shows how long to wait.
More free tools
- Face compare Upload two photos and get a similarity score, a match verdict and a plain-English reading of it.
- Look-alike test Upload a photo of each person and see how much the two faces have in common.
- Face blur Upload a photo and the faces in it are blurred for you. Keep the ones you want sharp, then download.
- Face pixelator Upload a photo and the faces in it are pixelated. Pick how coarse the blocks are, then download.
- Face crop Upload a photo and get a centred crop of every face: square, portrait or circle, one file each.
- Face detector Upload a photo to count the faces in it, see a numbered box on each one, and check which are clear enough to match.
- API cost calculator Price your monthly face workload on AWS Rekognition, Azure Face, Google Cloud Vision and SightRadar, operation by operation.
- Rekognition calculator Price an AWS Rekognition image workload in any region, tier by tier: face search, detection, storage and liveness.