Face Recognition On Raspberry Pi 3

In this experiment I tried to do face recognition on some of the faces contained in the photo using raspberry pi 3 and logitec webcam

IntermediateShowcase (no instructions)2 days7,186

Things used in this project

Hardware components

Raspberry Pi 3 Model B

Webcam, Logitech® HD Pro

Software apps and online services

Raspberry Pi Raspbian

OpenCV

Story

In this tutorial, we will try to create a face detection application based on OpenCV. We will create a dataset of photos with various expressions so that our facial recognition system is more accurate. Input images directly from our Raspberry Pi camera, so we can make face recognition in realtime.

We will install additional libraries for Python3 namely, dlib, face_recognition, and imutils.

For programming, we will use Python by utilizing libraries that were previously installed. There are 3 main python programs to be made. Namely face-encoding.py to encode all faces in the dataset. The second file is face-recognition-img.py to recognize faces with image input. And the 3rd file face-recognition-video.py to recognize faces in realtime with video input.

full tutorial at https://www.pyimagesearch.com/2018/06/18/face-recognition-with-opencv-python-and-deep-learning/

# PENGGUNAAN
# python face-recognition-video.py --cascade haarcascade_frontalface_default.xml --encodings encodings.pickle

# import library yang di perlukan
from imutils.video import VideoStream
from imutils.video import FPS
import face_recognition
import argparse
import imutils
import pickle
import time
import cv2

# Parsing Argumen
ap = argparse.ArgumentParser()
ap.add_argument("-c", "--cascade", required=True,
	help = "path to where the face cascade resides")
ap.add_argument("-e", "--encodings", required=True,
	help="path to serialized db of facial encodings")
args = vars(ap.parse_args())

# load pendeteksi wajah dari file cascade OpenCV
print("[INFO] loading encodings + face detector...")
data = pickle.loads(open(args["encodings"], "rb").read())
detector = cv2.CascadeClassifier(args["cascade"])

# Nyalakan Kamera
print("[INFO] Memulai Stream dari Pi Camera...")
vs = VideoStream(src=0).start()
time.sleep(2.0)

# Penghitung FPS (Frame per Second)
fps = FPS().start()

# loop dari semua frame yang di dapat
while True:
	# dapatkan frame, dan resize ke 500pixel agar lebih cepat
	frame = vs.read()
	frame = imutils.resize(frame, width=500)
	
	# Konversi ke grayscale dan konversi ke RGB
	gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
	rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)

	# deteksi wajah dari frame grayscale
	rects = detector.detectMultiScale(gray, scaleFactor=1.1, 
		minNeighbors=5, minSize=(30, 30),
		flags=cv2.CASCADE_SCALE_IMAGE)

   # Tampilkan kotak di wajah yang dideteksi
	boxes = [(y, x + w, y + h, x) for (x, y, w, h) in rects]

	encodings = face_recognition.face_encodings(rgb, boxes)
	names = []

	# loop di semua wajah yang terdeteksi
	for encoding in encodings:
		matches = face_recognition.compare_faces(data["encodings"],
			encoding)
		name = "Unknown"

		# check apakah ada wajah yang di kenali
		if True in matches:
			matchedIdxs = [i for (i, b) in enumerate(matches) if b]
			counts = {}
			for i in matchedIdxs:
				name = data["names"][i]
				counts[name] = counts.get(name, 0) + 1
			name = max(counts, key=counts.get)
		names.append(name)

	# loop di semua wajah yang sudah di kenali
	for ((top, right, bottom, left), name) in zip(boxes, names):
		# tampilkan nama di wajah yang di kenali
		cv2.rectangle(frame, (left, top), (right, bottom),
			(0, 255, 0), 2)
		y = top - 15 if top - 15 > 15 else top + 15
		cv2.putText(frame, name, (left, y), cv2.FONT_HERSHEY_SIMPLEX,
			0.75, (0, 255, 0), 2)

	# Tampilkan gambar di layar
	cv2.imshow("Frame", frame)
	key = cv2.waitKey(1) & 0xFF

	# tunggu tombol 1 untuk keluar
	if key == ord("q"):
		break

	# update FPS
	fps.update()

# tampilkan info FPS
fps.stop()
print("[INFO] elasped time: {:.2f}".format(fps.elapsed()))
print("[INFO] approx. FPS: {:.2f}".format(fps.fps()))

# cleanup
cv2.destroyAllWindows()
vs.stop()

# PENGGUNAAN
# python face-encoding.py --dataset dataset --encodings encodings.pickle --detection-method hog

# import library yang di perlukan
from imutils import paths
import face_recognition
import argparse
import pickle
import cv2
import os

# Parsing Argumen
ap = argparse.ArgumentParser()
ap.add_argument("-i", "--dataset", required=True,
	help="path to input directory of faces + images")
ap.add_argument("-e", "--encodings", required=True,
	help="path to serialized db of facial encodings")
ap.add_argument("-d", "--detection-method", type=str, default="cnn",
	help="face detection model to use: either `hog` or `cnn`")
args = vars(ap.parse_args())

# Ambil gambar dari folder dataset
print("[INFO] mendapatkan model wajah...")
imagePaths = list(paths.list_images(args["dataset"]))

# inisialiassi wajah yang di kenal
knownEncodings = []
knownNames = []

# loop di direktori gambar
for (i, imagePath) in enumerate(imagePaths):
	# Ambil nama dari masing-masing folder
	print("[INFO] Memproses gambar {}/{}".format(i + 1,
		len(imagePaths)))
	name = imagePath.split(os.path.sep)[-2]

	# konversi ke RGB (OpenCV ordering) ke dlib ordering (RGB)
	image = cv2.imread(imagePath)
	rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)

	# deteksi (x, y) koordinat dari kotak wajah
	boxes = face_recognition.face_locations(rgb,
		model=args["detection_method"])

	# Pemrosesan Wajah
	encodings = face_recognition.face_encodings(rgb, boxes)

	# loop semua proses encoding
	for encoding in encodings:
		knownEncodings.append(encoding)
		knownNames.append(name)

# dump the facial encodings + names to disk
print("[INFO] Memproses serialize encoding...")
data = {"encodings": knownEncodings, "names": knownNames}
f = open(args["encodings"], "wb")
f.write(pickle.dumps(data))
f.close()