Scribd
Upload
22 views2 pages

Track + Rec+name

The document outlines a Python script that utilizes OpenCV and DeepFace for real-time face recognition using a webcam. It captures video frames, detects faces, and compares them to a reference image to identify individuals. The script runs a separate thread for processing faces to ensure smooth video capture and display results with bounding boxes and labels on the video feed.

Uploaded by

mseif1573
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
22 views2 pages

Track + Rec+name

The document outlines a Python script that utilizes OpenCV and DeepFace for real-time face recognition using a webcam. It captures video frames, detects faces, and compares them to a reference image to identify individuals. The script runs a separate thread for processing faces to ensure smooth video capture and display results with bounding boxes and labels on the video feed.

Uploaded by

mseif1573
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as TXT, PDF, TXT or read online on Scribd

import cv2

import threading
import numpy as np
from deepface import DeepFace

# Initialize webcam
cap = [Link](0)
[Link](3, 640) # Width
[Link](4, 480) # Height

# Load and pre-process reference image


reference_name = "Reference Name" # Set this to the name you want displayed
reference_embedding = None
try:
ref_img = [Link]("[Link]")
if ref_img is not None:
# Pre-process once at startup
reference_embedding = [Link](ref_img, model_name='Facenet')[0]
["embedding"]
except Exception as e:
print(f"Reference error: {e}")

# Thread-safe variables
latest_frame = None
results = []
lock = [Link]()

def process_faces():
global latest_frame, results
while True:
frame = None
with lock:
if latest_frame is not None:
frame = latest_frame.copy()

if frame is None:
continue

try:
# Faster face detection with OpenCV
gray = [Link](frame, cv2.COLOR_BGR2GRAY)
faces = [Link](
[Link] + 'haarcascade_frontalface_default.xml'
).detectMultiScale(gray, 1.1, 4)

current_results = []
for (x, y, w, h) in faces:
label = "Unknown"
if reference_embedding is not None:
try:
# Face recognition
face_roi = frame[y:y+h, x:x+w]
face_embedding = [Link](face_roi,
model_name='Facenet')[0]["embedding"]
distance = [Link]([Link](face_embedding) -
[Link](reference_embedding))
if distance < 100: # Adjust this threshold as needed
label = reference_name
except:
pass

current_results.append(((x, y, w, h), label))

with lock:
results = current_results

except Exception as e:
print(f"Processing error: {e}")

# Start processing thread


[Link](target=process_faces, daemon=True).start()

while True:
ret, frame = [Link]()
if not ret:
break

# Update shared frame


with lock:
latest_frame = frame

# Display results
with lock:
current_results = [Link]()

# Draw on frame
for (x, y, w, h), label in current_results:
[Link](frame, (x, y), (x+w, y+h), (0, 255, 0), 2)
[Link](frame, label, (x, y-10),
cv2.FONT_HERSHEY_SIMPLEX, 0.9, (0, 255, 0), 2)

# Zoom preview
zoom = [Link](frame[y:y+h, x:x+w], (100, 100))
frame[10:110, 530:630] = zoom

# Display frame
[Link]('Face Recognition', frame)

if [Link](1) & 0xFF == ord('q'):


break

[Link]()
[Link]()

You might also like