Embedding
Definition
A compact numerical vector representation of a face produced by a neural network. The distance between two embeddings in the vector space is used as the similarity metric between two face images.
- Representation
- Numeric vector
- Produced by
- Neural network
- Comparison method
- Distance between vectors
Common questions
What distance measure compares two embeddings?+
Cosine similarity or Euclidean distance is typically used. A smaller distance indicates a greater likelihood that the two face images show the same person.
Can embedding similarity alone identify someone in court?+
No. It is a probabilistic match score from an algorithm and must be presented with its known error rates and limitations, not treated as a certain identification on its own.
Related terms
- ArcFace / FaceNet
- Two influential deep CNN facial recognition architectures. FaceNet (Google, 2015) used a triplet-loss training approach to learn facial embeddings. ArcFace (Deng et...
- False Match Rate (FMR)
- The proportion of non-mate comparisons (different individuals) that the system incorrectly scores as a match. Also called the false positive rate or...
- False Non-Match Rate (FNMR)
- The proportion of mate comparisons (same individual) that the system incorrectly scores as non-matching. Also called the false negative rate. A lower...
- Gallery vs Probe
- In facial recognition, the gallery is the reference database of enrolled face images; the probe is the query image being compared against...
- NIST FRVT
- The National Institute of Standards and Technology Face Recognition Vendor Testing programme, the primary independent benchmark for facial recognition algorithms, publishing ongoing...