#!/usr/bin/env python3 """ Simple Face Recognition App - Minimal GUI version Designed to work reliably on macOS """ import cv2 import numpy as np import os import json import csv import time from datetime import datetime, date def load_user_data(): """Load user data from user_data.json""" try: if os.path.exists("user_data.json"): with open("user_data.json", "r") as f: return json.load(f) return {} except Exception as e: print(f"❌ Error loading user data: {e}") return {} def load_recognizer(): """Load the face recognizer model""" try: recognizer = cv2.face.LBPHFaceRecognizer_create() model_file = "face_recognizer.yml" if os.path.exists(model_file): recognizer.read(model_file) print("✅ Loaded face recognition model") return recognizer else: print("⚠️ Face recognition model not found") return None except Exception as e: print(f"❌ Error loading recognizer: {e}") return None def log_attendance(user_id, user_name, attendance_data): """Log attendance with check-in/check-out logic""" try: today = date.today().strftime("%Y-%m-%d") if today not in attendance_data: attendance_data[today] = {} if user_name not in attendance_data[today]: # First time today - check-in attendance_data[today][user_name] = { "checkin": datetime.now().strftime("%H:%M:%S"), "checkout": "Not checked out" } print(f"✅ {user_name} checked in at {attendance_data[today][user_name]['checkin']}") return "Check-in" else: # Already checked in today - check-out if attendance_data[today][user_name]["checkout"] == "Not checked out": attendance_data[today][user_name]["checkout"] = datetime.now().strftime("%H:%M:%S") print(f"✅ {user_name} checked out at {attendance_data[today][user_name]['checkout']}") return "Check-out" else: # Update existing checkout time attendance_data[today][user_name]["checkout"] = datetime.now().strftime("%H:%M:%S") print(f"✅ {user_name} checkout updated to {attendance_data[today][user_name]['checkout']}") return "Check-out (Updated)" except Exception as e: print(f"❌ Error logging attendance: {e}") return "Error" def save_attendance_to_csv(attendance_data): """Save attendance data to CSV file""" try: with open("attendance_log.csv", "w", newline="") as csvfile: fieldnames = ["Date", "Name", "Check-in", "Check-out"] writer = csv.DictWriter(csvfile, fieldnames=fieldnames) writer.writeheader() for date_str, users in attendance_data.items(): for user_name, times in users.items(): writer.writerow({ "Date": date_str, "Name": user_name, "Check-in": times["checkin"], "Check-out": times["checkout"] }) except Exception as e: print(f"❌ Error saving attendance to CSV: {e}") def main(): """Main face recognition loop""" print("🚀 Starting Simple Face Recognition System") print("=" * 50) # Load data user_data = load_user_data() recognizer = load_recognizer() attendance_data = {} if not user_data: print("❌ No user data found. Please register users first.") return if not recognizer: print("❌ No face recognition model found. Please train the model first.") return print(f"✅ Loaded {len(user_data)} users") print("📋 Registered users:") for user_id, user_info in user_data.items(): print(f" - ID: {user_id}, Name: {user_info.get('name', 'Unknown')}") # Initialize camera print("\n📷 Initializing camera...") cap = cv2.VideoCapture(0) if not cap.isOpened(): print("❌ Failed to open camera") return # Set camera properties cap.set(cv2.CAP_PROP_FRAME_WIDTH, 640) cap.set(cv2.CAP_PROP_FRAME_HEIGHT, 480) cap.set(cv2.CAP_PROP_FPS, 30) print("✅ Camera initialized successfully") print("\n🎯 Face Recognition Active!") print("📝 Instructions:") print(" - Position your face in front of the camera") print(" - The system will detect and recognize faces automatically") print(" - Press 'q' to quit") print(" - Press 's' to show statistics") print("=" * 50) # Statistics total_detections = 0 successful_recognitions = 0 confidence_threshold = 120 # LBPH: lower is better, increased for better accuracy # Face cascade face_cascade = cv2.CascadeClassifier(cv2.data.haarcascades + 'haarcascade_frontalface_default.xml') try: while True: ret, frame = cap.read() if not ret: continue # Flip frame horizontally for mirror effect frame = cv2.flip(frame, 1) # Convert to grayscale for face detection gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY) # Detect faces faces = face_cascade.detectMultiScale(gray, 1.1, 4) # Process each face for (x, y, w, h) in faces: total_detections += 1 # Draw rectangle around face cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 255, 0), 2) # Face recognition with improved preprocessing face_roi = gray[y:y + h, x:x + w] face_roi = cv2.resize(face_roi, (200, 200)) # Increased size for better accuracy face_roi = cv2.equalizeHist(face_roi) # Histogram equalization for better contrast try: label, confidence = recognizer.predict(face_roi) if confidence < confidence_threshold: # Face recognized user_name = user_data.get(str(label), {}).get("name", f"User_{label}") # Add labels cv2.putText(frame, f"User: {user_name}", (x, y - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 255, 0), 2) cv2.putText(frame, f"Confidence: {confidence:.1f}", (x, y + h + 20), cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 255, 0), 2) # Log attendance (only once per session to avoid spam) if not hasattr(main, 'last_recognized') or main.last_recognized != (label, user_name): status = log_attendance(label, user_name, attendance_data) save_attendance_to_csv(attendance_data) print(f"📝 {user_name} - {status}") main.last_recognized = (label, user_name) successful_recognitions += 1 else: # Face not recognized cv2.putText(frame, "Unknown", (x, y - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 0, 255), 2) cv2.putText(frame, f"Confidence: {confidence:.1f}", (x, y + h + 20), cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 0, 255), 2) except Exception as e: print(f"Recognition error: {e}") cv2.putText(frame, "Error", (x, y - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 0, 255), 2) # Add statistics overlay cv2.putText(frame, f"Detections: {total_detections}", (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (255, 255, 255), 2) cv2.putText(frame, f"Recognitions: {successful_recognitions}", (10, 60), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (255, 255, 255), 2) cv2.putText(frame, "Press 'q' to quit, 's' for stats", (10, frame.shape[0] - 20), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255, 255, 255), 1) # Display frame cv2.imshow('Simple Face Recognition System', frame) # Handle key presses key = cv2.waitKey(1) & 0xFF if key == ord('q'): break elif key == ord('s'): print("\n📊 Current Statistics:") print(f" Total Detections: {total_detections}") print(f" Successful Recognitions: {successful_recognitions}") print(f" Recognition Rate: {(successful_recognitions/total_detections*100):.1f}%" if total_detections > 0 else " Recognition Rate: 0%") print(f" Confidence Threshold: {confidence_threshold}") print("=" * 30) except KeyboardInterrupt: print("\n⏹️ Interrupted by user") finally: # Cleanup cap.release() cv2.destroyAllWindows() print("\n📊 Final Statistics:") print(f" Total Detections: {total_detections}") print(f" Successful Recognitions: {successful_recognitions}") print(f" Recognition Rate: {(successful_recognitions/total_detections*100):.1f}%" if total_detections > 0 else " Recognition Rate: 0%") print("\n✅ Face recognition session ended") print("📁 Attendance data saved to attendance_log.csv") if __name__ == "__main__": main()