Detecting Multiple Faces

import cv2
import numpy as np

def analyse_group_photo(image_path):
    """Detect and analyse all faces in a group photo."""
    face_cascade = cv2.CascadeClassifier(
        cv2.data.haarcascades + "haarcascade_frontalface_default.xml"
    )
    eye_cascade = cv2.CascadeClassifier(
        cv2.data.haarcascades + "haarcascade_eye.xml"
    )

    image = cv2.imread(image_path)
    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

    # Equalise histogram for better detection in varied lighting
    gray_eq = cv2.equalizeHist(gray)

    faces = face_cascade.detectMultiScale(
        gray_eq, scaleFactor=1.05, minNeighbors=4, minSize=(40, 40)
    )

    print(f"=== Group Photo Analysis ===")
    print(f"Total faces detected: {len(faces)}")

    result = image.copy()
    face_data = []

    for i, (fx, fy, fw, fh) in enumerate(faces):
        cv2.rectangle(result, (fx, fy), (fx+fw, fy+fh), (0, 255, 0), 2)
        cv2.putText(result, f"#{i+1}", (fx, fy-5),
                   cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0,255,0), 1)

        # Detect eyes within each face region
        face_roi_gray = gray_eq[fy:fy+fh, fx:fx+fw]
        eyes = eye_cascade.detectMultiScale(face_roi_gray, scaleFactor=1.1, minNeighbors=5)

        face_data.append({
            "id": i + 1,
            "position": (fx, fy),
            "size": (fw, fh),
            "area": fw * fh,
            "eyes_detected": len(eyes),
        })

        # Draw eyes
        for (ex, ey, ew, eh) in eyes:
            cv2.circle(result, (fx+ex+ew//2, fy+ey+eh//2), ew//2, (255, 0, 0), 2)

    # Sort by size (largest face first = likely closest person)
    face_data.sort(key=lambda x: x["area"], reverse=True)
    for face in face_data:
        print(f"  Face {face['id']}: size={face['size'][0]}x{face['size'][1]}, eyes={face['eyes_detected']}")

    cv2.imwrite("group_analysis.jpg", result)
    return face_data

analyse_group_photo("group.jpg")