Group Photos by Face in Python: One Album per Person

Phone galleries, family archives, a photographer's backlog: where are all the photos of this person? Here is how to group photos by face in Python: detect every face, match it in a face repository, and sort the library into one album per person. No model to download, no dlib to compile.

Every number below comes from a live run on 24 photos from two outings, a camping trip and a beach picnic.

Want to sort your own library? Get a key for the Face Analyzer API.

Step 1: create a face repository

import io
import os
import shutil
import requests
from concurrent.futures import ThreadPoolExecutor
from PIL import Image, ImageOps

BASE = "https://faceanalyzer-ai.p.rapidapi.com"
HEADERS = {
    "x-rapidapi-host": "faceanalyzer-ai.p.rapidapi.com",
    "x-rapidapi-key": "YOUR_API_KEY",
}
LIBRARY = "my-photo-library"
MIN_SIMILARITY = 90

r = requests.post(
    f"{BASE}/create-facial-repository",
    headers=HEADERS,
    data={"repository_id": LIBRARY},
)
print(r.json())

Step 2: detect and crop every face

def detect_faces(path):
    """Return the photo path and the bounding box of every face in it."""
    with open(path, "rb") as f:
        r = requests.post(f"{BASE}/faceanalysis", headers=HEADERS, files={"image": f})
    return path, [face["boundingBox"] for face in r.json()["body"]["faces"]]

def crop_face(path, box, margin=0.4):
    """Cut one face out of the photo, with a margin, as JPEG bytes."""
    im = ImageOps.exif_transpose(Image.open(path)).convert("RGB")
    w, h = im.size
    x1, y1 = box["topLeft"]["x"] * w, box["topLeft"]["y"] * h
    x2, y2 = box["bottomRight"]["x"] * w, box["bottomRight"]["y"] * h
    mx, my = (x2 - x1) * margin, (y2 - y1) * margin
    face = im.crop((
        int(max(0, x1 - mx)), int(max(0, y1 - my)),
        int(min(w, x2 + mx)), int(min(h, y2 + my)),
    ))
    buf = io.BytesIO()
    face.save(buf, "JPEG", quality=92)
    return buf.getvalue()

The repository search looks at the main face of the image it receives, so each face is sent as its own crop.

Step 3: match each face or start a new person

def who_is(face_jpg):
    """Return the label of the closest known person, or None for a new face."""
    r = requests.post(
        f"{BASE}/search-face-in-repository",
        headers=HEADERS,
        files={"image": ("face.jpg", face_jpg)},
        data={"repository_id": LIBRARY},
    )
    matches = [
        m for m in r.json()["body"].get("FaceMatches", [])
        if m["Similarity"] >= MIN_SIMILARITY
    ]
    if not matches:
        return None
    return max(matches, key=lambda m: m["Similarity"])["ExternalImageId"]

def remember(face_jpg, person):
    """Save the face under the person's label, so later photos match it too."""
    requests.post(
        f"{BASE}/save-face-in-repository",
        headers=HEADERS,
        files={"image": ("face.jpg", face_jpg)},
        data={"repository_id": LIBRARY, "external_id": person, "max_faces": "1"},
    )

people = {}  # person label -> names of the photos they appear in

def sort_photos(folder):
    """Detect faces in parallel, then match each face to a person in order."""
    paths = sorted(os.path.join(folder, n) for n in os.listdir(folder))
    with ThreadPoolExecutor(max_workers=4) as pool:
        detected = list(pool.map(detect_faces, paths))
    for path, boxes in detected:
        for box in boxes:
            face_jpg = crop_face(path, box)
            person = who_is(face_jpg)
            if person is None:
                person = f"person_{len(people) + 1}"
                people[person] = set()
            remember(face_jpg, person)
            people[person].add(path)
    return sum(len(boxes) for _, boxes in detected)

faces = sort_photos("photos")
print(faces, "faces,", len(people), "face groups")
# 54 faces, 16 face groups

Step 4: one album per person

MIN_PHOTOS = 3

def build_albums(out_dir="albums"):
    """Copy each photo into the album of every person in it."""
    shutil.rmtree(out_dir, ignore_errors=True)
    for person, paths in people.items():
        album = person if len(paths) >= MIN_PHOTOS else "unsorted"
        os.makedirs(os.path.join(out_dir, album), exist_ok=True)
        for path in paths:
            shutil.copy(path, os.path.join(out_dir, album, os.path.basename(path)))
    for album in sorted(os.listdir(out_dir)):
        print(album, len(os.listdir(os.path.join(out_dir, album))), "photos")

build_albums()

person_10 6 photos
person_12 4 photos
person_13 4 photos
person_14 5 photos
person_2 6 photos
person_3 6 photos
person_5 7 photos
person_6 5 photos
person_9 3 photos
unsorted 7 photos

Nine albums for the nine people: the two campers and the seven picnic friends. Every album contains a single person, checked by eye. Faces seen once or twice (a head turned away, a passer-by out of focus) go to unsorted.

Step 5: new photos join the right album

before = {person: set(paths) for person, paths in people.items()}
sort_photos("new_photos")
for person, paths in people.items():
    for path in sorted(paths - before.get(person, set())):
        print(os.path.basename(path), "->", person)
build_albums()

IMG_5064932.jpg -> person_3
IMG_8021122.jpg -> person_9

Under 3 seconds, no re-clustering.

Why not face_recognition + DBSCAN?

	face_recognition + DBSCAN	Face Analyzer API
Install	dlib source build (CMake, C++)	requests and Pillow
Last release	1.3.0, February 2020	hosted
New photos	re-cluster, labels can change	one search per face, stable labels
Tuning	eps and min_samples	one similarity threshold
Children	README warns it mixes them up at 0.6	same code for every face

Production tips

• One repository per user, deleted when they turn the feature off
• Face grouping is biometric processing under GDPR Article 9: make it opt-in
• Let users merge and rename albums
• Run the first pass as a background job

Full guide: group photos by face on ai-engine.net.

Sources: face_recognition, dlib on PyPI, GDPR Article 9, test photos from Pexels (Kamaji Ogino, Thirdman).

👉 Grab a key from the Face Analyzer API page and sort your own photos.