embedding_distance: Compute Distance Between Two Embeddings

View source: R/embeddings.R

embedding_distanceR Documentation

Compute Distance Between Two Embeddings

Description

Calculates the distance or similarity between two face embedding vectors.

Usage

embedding_distance(
  emb1,
  emb2,
  metric = c("cosine", "euclidean", "euclidean_l2")
)

Arguments

emb1

Numeric vector. First embedding.

emb2

Numeric vector. Second embedding.

metric

Character. Distance metric to use:

  • "cosine" - Cosine distance (1 - cosine similarity). Recommended for ArcFace.

  • "euclidean" - Euclidean (L2) distance.

  • "euclidean_l2" - Euclidean distance on L2-normalized vectors.

Details

For ArcFace and other angular-margin trained models, cosine distance is recommended as it aligns with the training objective.

Cosine distance ranges from 0 (identical) to 2 (opposite). Typical thresholds for same-person verification:

  • ArcFace + cosine: ~0.68

  • Facenet512 + cosine: ~0.30

Value

Numeric distance value. Lower values indicate more similar faces.

Examples

## Not run: 
emb1 <- get_embedding("face1.jpg")$embedding
emb2 <- get_embedding("face2.jpg")$embedding

# Cosine distance (recommended)
embedding_distance(emb1, emb2, metric = "cosine")

# Euclidean distance
embedding_distance(emb1, emb2, metric = "euclidean")

## End(Not run)


r4lineups documentation built on Nov. 10, 2026, 1:08 a.m.