Using the face_recognition Library in Python: Full Guide for Beginners

Face recognition has gone from sci-fi to daily reality — it’s used in phone unlocks, surveillance, and smart apps. Python makes it surprisingly easy to implement thanks to the powerful face_recognition library.

This tutorial will walk you through everything you need to know: installation, detecting faces, recognizing people, and building a simple face recognition system — all using just a few lines of Python code.

What is `face_recognition`?

face_recognition is a Python library built on top of dlib and deep learning. It allows you to:

Detect faces in images or video
Recognize and identify faces
Extract facial features and compare faces
Label known people in photos

It’s known for being:

Extremely accurate (based on deep learning)
Very easy to use
Open-source and actively maintained

Installation

First, make sure you’re using Python 3.6–3.11.

1. Install CMake (required for dlib)

pip install cmake

2. Install dlib and face_recognition

pip install dlib
pip install face_recognition

Note: On Windows, you might need to install Visual Studio Build Tools. On macOS, install brew install cmake.

📂 Prepare Your Images

Create a folder like:

face_project/
├── known/
│   ├── alice.jpg
│   └── bob.jpg
├── unknown/
│   └── test.jpg

Place clear, front-facing images in known/
Place the test image in unknown/

Basic Face Detection

import face_recognition
import cv2

image = face_recognition.load_image_file("unknown/test.jpg")
face_locations = face_recognition.face_locations(image)

print(f"Found {len(face_locations)} face(s) in the image.")

Basic Face Recognition (Compare Faces)

known_image = face_recognition.load_image_file("known/alice.jpg")
unknown_image = face_recognition.load_image_file("unknown/test.jpg")

alice_encoding = face_recognition.face_encodings(known_image)[0]
unknown_encoding = face_recognition.face_encodings(unknown_image)[0]

results = face_recognition.compare_faces([alice_encoding], unknown_encoding)

if results[0]:
    print("This is Alice!")
else:
    print("Not Alice.")

Identify Multiple People in a Photo

import os

known_encodings = []
known_names = []

for filename in os.listdir("known"):
    image = face_recognition.load_image_file(f"known/{filename}")
    encoding = face_recognition.face_encodings(image)[0]
    known_encodings.append(encoding)
    known_names.append(os.path.splitext(filename)[0])

# Load unknown image
image = face_recognition.load_image_file("unknown/test.jpg")
face_locations = face_recognition.face_locations(image)
face_encodings = face_recognition.face_encodings(image, face_locations)

for (top, right, bottom, left), face_encoding in zip(face_locations, face_encodings):
    matches = face_recognition.compare_faces(known_encodings, face_encoding)
    
    name = "Unknown"
    if True in matches:
        first_match_index = matches.index(True)
        name = known_names[first_match_index]

    print(f"Detected: {name}")

Real-Time Face Recognition with Webcam

import face_recognition
import cv2

# Load known face
known_image = face_recognition.load_image_file("known/alice.jpg")
known_encoding = face_recognition.face_encodings(known_image)[0]
known_names = ["Alice"]

video_capture = cv2.VideoCapture(0)

while True:
    ret, frame = video_capture.read()

    small_frame = cv2.resize(frame, (0, 0), fx=0.25, fy=0.25)
    rgb_small_frame = cv2.cvtColor(small_frame, cv2.COLOR_BGR2RGB)

    face_locations = face_recognition.face_locations(rgb_small_frame)
    face_encodings = face_recognition.face_encodings(rgb_small_frame, face_locations)

    for (top, right, bottom, left), face_encoding in zip(face_locations, face_encodings):
        matches = face_recognition.compare_faces([known_encoding], face_encoding)

        name = "Unknown"
        if True in matches:
            name = known_names[0]

        # Scale back up
        top *= 4; right *= 4; bottom *= 4; left *= 4
        cv2.rectangle(frame, (left, top), (right, bottom), (0, 255, 0), 2)
        cv2.putText(frame, name, (left, top - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.9, (255, 255, 255), 2)

    cv2.imshow('Video', frame)
    
    if cv2.waitKey(1) == ord('q'):
        break

video_capture.release()
cv2.destroyAllWindows()

Tips for Better Accuracy

Use high-resolution images for face encoding.
Make sure the faces are front-facing and well-lit.
For faster performance, resize frames to 1/4 scale (as shown above).

Advanced Features in `face_recognition`

Feature	Method
Get face landmarks	`face_recognition.face_landmarks()`
Find facial features	Eyes, nose, lips, jaw
Compare multiple faces	`compare_faces()` with multiple encodings
Get face distances	`face_recognition.face_distance()`

Troubleshooting

Problem	Solution
No faces found	Use clear, front-facing images
`IndexError` on encoding	Ensure `face_encodings()` returns a result
Slow webcam performance	Resize frame to 1/4 or use a GPU build of dlib

What Can You Build with `face_recognition`?

Smart door lock using Raspberry Pi
Attendance system for schools
Face-sorting photo gallery
Real-time face-based tagging for security cameras

Conclusion

The face_recognition library makes face detection and recognition in Python extremely accessible, even for beginners. With just a few lines of code, you can build impressive, real-world projects that leverage computer vision.

You now know how to:

Detect and identify faces in images and videos
Compare faces with known profiles
Build real-time face recognition with a webcam