from cv2 import cv2
face_cascade = cv2.CascadeClassifier('data//haarcascade_frontalface_alt.xml')
cap = cv2.VideoCapture(0)
while(cap.isOpened()):
ret,frame = cap.read()
gray = cv2.cvtColor(frame,cv2.COLOR_BGR2GRAY)
faces = face_cascade.detectMultiScale(gray,scaleFactor = 1.5,minNeighbors = 5)
for(x,y,w,h) in faces:
print(x,y,w,h)
roi_gray = gray[y:y+h,x:x+w]
roi_color = frame[y:y+h,x:x+w]
color = (255,0,0) #BGR
stroke = 2
cv2.rectangle(frame,(x,y),(x+w,y+h),color,stroke )
font = cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(frame,"Face Detected",(15,25),font ,1,color = (255,0,0),thickness=1)
cv2.imshow('frame',frame)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
cap.release()
cv2.destroyAllWindows()
h = img.shape[0]
#image = []
for i in range(0,w):
for j in range(0,h):
for c in range(3):
tmp = int(img[j,i,c]*alpha + bias)
if tmp > 255:
tmp = 255
elif tmp < 0:
tmp = 0
img[j,i,c] = tmp
return img
# 获取分类器
haar = cv2.CascadeClassifier(r'E:\ProgramData\Anaconda3\envs\tenserflow02\Lib\site-packages\cv2\data\haarcascade_frontalface_default.xml')
# 打开摄像头 参数为输入流，可以为摄像头或视频文件
camera = cv2.VideoCapture(0)
n = 1
while 1:
if (n <= 5000):
print('It`s processing %s image.' % n)
# 读帧
success, img = camera.read()
gray_img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
faces = haar.detectMultiScale(gray_img, 1.3, 5)
for f_x, f_y, f_w, f_h in faces:
face = img[f_y:f_y+f_h, f_x:f_x+f_w]
face = cv2.resize(face, (64,64))
import numpy as np
from cv2 import cv2
import os
import face_recognition
# 人脸识别分类器
faceCascade = cv2.CascadeClassifier(
r'/Users/haodongsheng/.local/share/virtualenvs/hellopy-X998b6LV/lib/python3.7/site-packages/cv2/data/haarcascade_frontalface_default.xml'
)
save_dir = r'/Users/haodongsheng/Documents/Prog/mongoMaster/face/'
def get_video_path(dir_path, target_path):
list_ = os.listdir(dir_path)
for i in range(0, len(list_)):
path = os.path.join(dir_path, list_[i])
if os.path.isdir(path):
get_video_path(path, target_path)
if os.path.isfile(path):
temp_path = str.lower(path)
if temp_path.endswith(".mp4"):
recognize(path, target_path)
def recognize(file_path, target_path, tolerance=0.5):
global faceCascade
global save_dir
# 开启摄像头
cap = cv2.VideoCapture(file_path)
from cv2 import cv2
import numpy as np
video = cv2.VideoCapture("video.mp4")
car_classifier = cv2.CascadeClassifier("cars.xml")
people_classifier = cv2.CascadeClassifier("haarcascade_fullbody.xml")
while True:
ret, frame = video.read()
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
cars = car_classifier.detectMultiScale(gray, 1.3, 3)
people = people_classifier.detectMultiScale(gray, 1.1, 2)
for (x, y, w, h) in cars:
cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 255, 0), 3)
for (x, y, w, h) in people:
cv2.rectangle(frame, (x, y), (x + w, y + h), (255, 255, 0), 3)
cv2.imshow("video", frame)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
video.release()
cv2.destroyAllWindows()
import glob
import cv2.cv2 as cv2
if __name__ == "__main__":
path_to_xml_classifier_file = "../classifier/cascade.xml"
path_to_test_images = "../../Hauptprojekt/debugImages/found_vehicles/"
files = glob.glob('{0}/*.png'.format(path_to_test_images))
for file in files:
image = cv2.imread(file)
gray_image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
classifier = cv2.CascadeClassifier(path_to_xml_classifier_file)
lps = classifier.detectMultiScale(gray_image)
for (x, y, w, h) in lps:
cv2.rectangle(image, (x, y), (x + w, y + h), (255, 0, 0), 2)
cv2.imshow('img', image)
cv2.waitKey(0)
cv2.destroyAllWindows()
def facialRecognition(drone):
faceCascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
rectangleColor = (0,165,255)
try:
drone.connect()
drone.wait_for_connection(60.0)
container = av.open(drone.get_video_stream())
tracker = dlib.correlation_tracker()
trackingFace = False
frameSkip = 300 #to eliminate initial lag
while True:
for frame in container.decode(video=0):
if 0 < frameSkip:
frameSkip = frameSkip - 1
continue
image = cv2.cvtColor(numpy.array(frame.to_image()), cv2.COLOR_RGB2BGR)
frame = numpy.array(frame.to_image()) #convert frame
facialFrame = frame #make a copy of frame
if not trackingFace:
grey = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
faces = faceCascade.detectMultiScale(grey, 1.3, 5)
maxArea = 0
x = 0
y = 0
w = 0
h = 0
for (_x,_y,_w,_h) in faces:
if _w*_h > maxArea:
x = int(_x)
y = int(_y)
w = int(_w)
h = int(_h)
maxArea = w*h
if maxArea > 0 :
tracker.start_track(frame,dlib.rectangle(x-10,y-20,x+w+10,y+h+20))
trackingFace = True
if trackingFace:
trackingQuality = tracker.update(frame)
if trackingQuality >= 8.75:
tracked_position = tracker.get_position()
t_x = int(tracked_position.left())
t_y = int(tracked_position.top())
t_w = int(tracked_position.width())
t_h = int(tracked_position.height())
cv2.rectangle(facialFrame,(t_x, t_y),(t_x + t_w , t_y + t_h),rectangleColor ,2)
else:
trackingFace = False
cv2.imshow('Facial Recognition',facialFrame)
cv2.waitKey(1)
except Exception as ex:
exc_type, exc_value, exc_traceback = sys.exc_info()
traceback.print_exception(exc_type, exc_value,exc_traceback)
print(ex)
except KeyboardInterrupt as ex:
print('KEYBOARD INTERRUPT')
finally:
cv2.destroyAllWindows()
from cv2 import cv2
face_cascade = cv2.CascadeClassifier("haarcascade_frontalface_default.xml")
img = cv2.imread("photo.jpg")
gray_img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
faces = face_cascade.detectMultiScale(gray_img,
scaleFactor=1.05,
minNeighbors=5)
for x, y, w, h in faces:
img = cv2.rectangle(img, (x, y), (x + w, y + h), (0, 255, 0), 3)
resized = cv2.resize(img, (int(img.shape[1] / 3), int(img.shape[0] / 3)))
cv2.imshow("Gray", resized)
cv2.waitKey(0)
cv2.destroyAllWindows()
from keras.preprocessing.image import img_to_array
import imutils
from cv2 import cv2
from keras.models import load_model
import numpy as np
import json
# parameters for loading data and images
detection_model_path = 'models/haarcascade_frontalface_default.xml'
emotion_model_path = 'models/_mini_XCEPTION.102-0.66.hdf5'
# hyper-parameters for bounding boxes shape
# loading models
face_detection = cv2.CascadeClassifier(detection_model_path)
emotion_classifier = load_model(emotion_model_path, compile=False)
EMOTIONS = [
"angry", "disgust", "scared", "happy", "sad", "surprised", "neutral"
]
path = '../Assets/test.png'
while True:
frame = cv2.imread(path)
if frame is None:
print('Reading while writing')
continue
# resize the frame
frame = imutils.resize(frame, width=300)
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
faces = face_detection.detectMultiScale(gray,
scaleFactor=1.1,
minNeighbors=5,
minSize=(30, 30),
#!/usr/bin/env python
# -*- encoding: utf-8 -*-
import os
import numpy as np
from cv2 import cv2
#获取当前路径
dir_path = os.path.abspath(os.path.dirname(__file__))
# 加载人脸识别分类器
faceCascade = cv2.CascadeClassifier(
dir_path + '\model\haarcascade_frontalface_default.xml')
# 加载识别眼睛的分类器
eyeCascade = cv2.CascadeClassifier(dir_path + '\model\haarcascade_eye.xml')
# 开启摄像头
cap = cv2.VideoCapture(0)
ok = cap.isOpened()
print("camera open is:", cap.isOpened())
while ok:
# 读取摄像头中的图像，ok为是否读取成功的判断参数
ok, img = cap.read()
# 转换成灰度图像
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# 进行人脸检测
faces = faceCascade.detectMultiScale(
gray,
scaleFactor=1.2,
minNeighbors=5, #
minSize=(32, 32) # 识别框最小尺度大小
from cv2 import cv2
import numpy as np
img = cv2.imread('with_mask203.jpg')
face_cascade = cv2.CascadeClassifier(
'C:/Users/truongnn/work_env/Lib/site-packages/cv2/data/haarcascade_frontalface_default.xml'
)
mouth = cv2.CascadeClassifier(
'C:/Users/truongnn/work_env/Lib/site-packages/cv2/data/haarcascade_smile.xml'
)
# cv2.imshow('image',img)
img_gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
faces = face_cascade.detectMultiScale(img_gray, 1.1, 5)
for (x, y, w, h) in faces:
cv2.rectangle(img, (x, y), (x + w, y + h), (0, 0, 255), 1)
#cv2.putText(img, 'No Mask', (x, y-10), cv2.FONT_ITALIC, 0.8, (0,0,255), 1)
roi_gray = img_gray[y:y + h, x:x + w]
roi_color = img[y:y + h, x:x + w]
is_mouth = mouth.detectMultiScale(roi_gray)
for (a, b, c, d) in is_mouth:
cv2.rectangle(roi_color, (a, b), (a + c, b + d), (0, 0, 255), 1)
# if re:
# cv2.putText(img, 'No Mask', (x, y-10), cv2.FONT_ITALIC, 0.8, (0,0,255), 1)
# else:
# cv2.putText(img, 'Masked', (x, y-10), cv2.FONT_ITALIC, 0.8, (0,0,255), 1)
cv2.imshow('image', img)
cv2.waitKey(0)
cv2.destroyAllWindows()
import os
from cv2 import cv2 as cv
path = os.getcwd()
print(path)
cascade = cv.CascadeClassifier(path + "/datas/haar_cascade_files/haarcascade_frontalface_default.xml")
cascade_eye = cv.CascadeClassifier(path + "/datas/haar_cascade_files/haarcascade_eye.xml")
# cascade_nose = cv.CascadeClassifier(path + "/datas/haar_cascade_files/haarcascade_mcs_nose.xml")
img = cv.imread(path + "/datas/images/faces.jpg")
imgGray = cv.cvtColor(img, cv.COLOR_BGR2GRAY)
faces = cascade.detectMultiScale(imgGray, 1.1, 4)
eyes = cascade_eye.detectMultiScale(imgGray, 1.1, 4)
for (x, y, w, h) in faces:
cv.rectangle(img, (x, y), (x + w, y + h), (255, 0, 0), 2)
for (a, b, c, d) in eyes:
cv.rectangle(img, (a, b), (a + c, b + d), (0, 255, 0), 2)
img_resize = cv.resize(img, (1280,960))
cv.imshow("Result", img_resize)
cv.waitKey(0)
import sys
import numpy as np
from cv2 import cv2 as cv
haar_face = cv.CascadeClassifier("haarcascade_frontalface_default.xml")
haar_eyes = cv.CascadeClassifier("haarcascade_eye.xml")
video_capture = cv.VideoCapture(0)
if not video_capture.isOpened():
print("Cannot open camera!!!")
exit()
while True:
ret, frame = video_capture.read()
if not ret:
print("Can't receive frame (stream end?). Exiting ...")
break
gray = cv.cvtColor(frame, cv.COLOR_BGR2GRAY)
deteced_faces = haar_face.detectMultiScale(gray,
scaleFactor=1.1,
minNeighbors=5,
minSize=(30, 30))
for (x, y, w, h) in deteced_faces:
cv.rectangle(frame, (x, y), (x + w, y + h), (255, 0, 0), 3)
eye_color = frame[y:y + h, x:x + w]
eye_gray = gray[y:y + h, x:x + w]
deteced_eye = haar_eyes.detectMultiScale(eye_gray,
def trainer(request):
# Creating a recognizer to train
recognizer = cv2.face.LBPHFaceRecognizer_create()
# train with the default data
detector = cv2.CascadeClassifier(
"media/haarcascade_frontalface_default.xml")
path = 'media/dataset'
# To get all the images, we need corresponing id
def getImagesWithID(path):
# And putting them in 'f' and join method is appending the f(file name) to the path with the '/'
imagePaths = [os.path.join(path, f) for f in os.listdir(path)
] #concatinate the path with the image name
#print imagePaths
ids = []
# Now, we loop all the images and store that userid and the face with different image list
faceSamples = []
for imagePath in imagePaths:
# First we have to open the image then we have to convert it into numpy array
PIL_img = Image.open(imagePath).convert(
'L') #convert it to grayscale
# converting the PIL image to numpy array
# @params takes image and convertion format
img_numpy = np.array(PIL_img, 'uint8')
# Now we need to get the user id, which we can get from the name of the picture
# for this we have to slit the path() i.e dataset/user.1.7.jpg with path splitter and then get the second part only i.e. user.1.7.jpg
# Then we split the second part with . splitter
# Initially in string format so hance have to convert into int format
id = int(
os.path.split(imagePath)[-1].split(".")[1]
) # -1 so that it will count from backwards and slipt the second index of the '.' Hence id
# extract the face from the training image sample
faces = detector.detectMultiScale(img_numpy)
# If a face is there then append that in the list as well as Id of it
for (x, y, w, h) in faces:
# images
faceSamples.append(img_numpy[y:y + h, x:x + w])
# label
ids.append(id)
return faceSamples, ids
# Fetching ids and faces
faces, ids = getImagesWithID(path)
#Training the recognizer
# For that we need face samples and corresponding labels
recognizer.train(faces, np.array(ids))
# Save the recogzier state so that we can access it later
recognizer.write('media/trainer/trainingData.yml')
cv2.destroyAllWindows()
return redirect('/register')
def detect(request):
faceDetect = cv2.CascadeClassifier(
'media/haarcascade_frontalface_default.xml')
# creating recognizer
rec = cv2.face.LBPHFaceRecognizer_create()
# loading the training data
rec.read('media/trainer/trainingData.yml')
font = cv2.FONT_HERSHEY_SIMPLEX
# assign id = 0
id = 0
# creating name array
#names = ['None', 'Akash', 'Sabin', 'Biplov', 'Dipesh']
#fetching data from database
em = Employee.objects.values_list('name', flat=True)
names = list(em)
cam = cv2.VideoCapture(0)
cam.set(3, 640) # set video widht
cam.set(4, 480) # set video height
# Define min window size to be recognized as a face
minW = 0.1 * cam.get(3)
minH = 0.1 * cam.get(4)
while (True):
# cam.read will return the status variable and the captured colored image
_, img = cam.read()
img = cv2.flip(img, 1)
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
faces = faceDetect.detectMultiScale(
gray,
scaleFactor=1.2,
minNeighbors=5,
minSize=(int(minW), int(minH)),
)
for (x, y, w, h) in faces:
cv2.rectangle(img, (x, y), (x + w, y + h), (0, 255, 0), 2)
id, conf = rec.predict(
gray[y:y + h, x:x + w]) #This will predict the id of the face
if (conf < 100):
id = names[id]
conf = " {0}".format(round(100 - conf))
# performs attendance only when we have 35 or more accuracy
if (int(conf) > 35):
date = datetime.datetime.now().strftime("%Y-%m-%d")
old = Attendance.objects.filter(name=id,
date__date=date).first()
if (old == None):
at = Attendance()
at.name = id
at.save()
else:
messages.info(request, 'oops!! not detected!!')
else:
id = "unknown"
conf = " {0}".format(round(100 - conf))
cv2.putText(img, str(id), (x + 5, y - 5), font, 1, (255, 255, 255),
2)
cv2.putText(img, str(conf), (x + 5, y + h - 5), font, 1,
(255, 255, 0), 1)
cv2.imshow("Face", img)
k = cv2.waitKey(10) & 0xff # Press 'ESC' for exiting video
if k == 27:
break
cam.release()
cv2.destroyAllWindows()
return redirect('/attendance')
app.config['MAIL_PASSWORD'] = '******'
app.config['MAIL_USE_TLS'] = False
app.config['MAIL_USE_SSL'] = True
mail = Mail(app)
mysql = MySQL(app)
#courseid=''
import csv
from datetime import datetime
#from app import courseid
import cv2
import face_recognition
import os
import numpy as np
face_cascade = cv2.CascadeClassifier("haarcascade_frontalface_alt2.xml")
ds_factor = 0.6
filename = ''
class VideoCamera(object):
#courseid=''
def __init__(self):
self.video = cv2.VideoCapture(0)
def __del__(self):
self.video.release()
path = 'E:/flask_demo/static/images'
images = []
from cv2 import cv2
import dlib
import math
import time
car_detect = cv2.CascadeClassifier('car_detect_harrcascade.xml')
video = cv2.VideoCapture('highway.mp4')
ret, image1 = video.read()
# Dinh nghia cac tham so dai , rong
f_width = 1280
f_height = 720
# Cai dat tham so : so diem anh / 1 met, o day dang de 1 pixel = 1 met
pixels_per_meter = 1
# Cac tham so phuc vu tracking
frame_idx = 0
car_number = 0
fps = 0
carTracker = {}
carNumbers = {}
carStartPosition = {}
carCurrentPosition = {}
speed = [None] * 1000
# fourcc=cv2.VideoWriter_fourcc(*'XVID')
# out = cv2.VideoWriter('outpy.mp4',fourcc,20.0, (f_width,f_height))
# Ham xoa cac tracker khong tot
def __init__(self, Id, name):
self.Id = Id
self.name = name
self.detector = cv2.CascadeClassifier("Assets\\haarcascade\\haarcascade_frontalface_default.xml")
self.RES_W = 640 # 1280 # 640 # 256 # 320 # 480 # pixels
self.RES_H = 480 # 720 # 480 # 144 # 240 # 360 # pixels
def scan():
# load model
model = model_from_json(open("fer.json", "r").read())
# load weights
model.load_weights('fer.h5')
face_haar_cascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
cap = cv2.VideoCapture(0)
while True:
ret, test_img = cap.read() # captures frame and returns boolean value and captured image
if not ret:
continue
gray_img = cv2.cvtColor(test_img, cv2.COLOR_BGR2GRAY)
faces_detected = face_haar_cascade.detectMultiScale(gray_img, 1.32, 5)
for (x, y, w, h) in faces_detected:
cv2.rectangle(test_img, (x, y), (x + w, y + h), (255, 0, 0), thickness=7)
roi_gray = gray_img[y:y + w, x:x + h] # cropping region of interest i.e. face area from image
roi_gray = cv2.resize(roi_gray, (48, 48))
img_pixels = image.img_to_array(roi_gray)
img_pixels = np.expand_dims(img_pixels, axis=0)
img_pixels /= 255
predictions = model.predict(img_pixels)
# find max indexed array
max_index = np.argmax(predictions[0])
emotions = ('angry', 'disgust', 'fear', 'happy', 'sad', 'surprise', 'neutral')
predicted_emotion = emotions[max_index]
cv2.putText(test_img, predicted_emotion, (int(x), int(y)), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 255), 2)
resized_img = cv2.resize(test_img, (600, 350))
cv2.imshow('Emotion Melody', resized_img)
key = cv2.waitKey(30) & 0xff
if key == 13: # wait until 'enter' key is pressed
break
cap.release()
cv2.destroyAllWindows
mp = '/Applications/VLC.app/Contents/MacOS/VLC'
if predicted_emotion == "happy":
file = '/Users/ashmika/Desktop/face-detection/songs/happy/'
lab = Label(root, text="You looked happy, so an energetic happy playlist was created!")
lab.pack()
subprocess.call([mp, file])
if predicted_emotion == "sad":
lab=Label(root,text = "You looked sad, a sad songs playlist was created")
lab.pack()
file = '/Users/ashmika/Desktop/face-detection/songs/sad/'
subprocess.call([mp, file])
if predicted_emotion == "angry":
lab=Label(root,text = "You looked angry, hope that playlist put you in a good mood!")
lab.pack()
file = '/Users/ashmika/Desktop/face-detection/songs/angry/'
subprocess.call([mp, file])
if predicted_emotion == "neutral":
lab=Label(root,text = "You were calm, hope that playlist matched your vibe!")
lab.pack()
file = '/Users/ashmika/Desktop/face-detection/songs/neutral/'
subprocess.call([mp, file])
from cv2 import cv2
import numpy as np
face_cascade = cv2.CascadeClassifier(
'/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/cv2/data/haarcascade_frontalface_alt2.xml'
)
cap = cv2.VideoCapture(0)
while (True):
# Capture frame by frame
ret, frame = cap.read()
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
faces = face_cascade.detectMultiScale(gray, scaleFactor=4, minNeighbors=5)
for (x, y, w, h) in faces:
# print(x,y,w,h)
roi_gray = gray[y:y + h, x:x + w]
roi_bgr = frame[y:y + h, x:x + w]
img_item = 'face_image.png'
cv2.imwrite(img_item, roi_gray)
#draw square
color = (0, 0, 255)
stroke = 3
end_cordx = x + w
end_cordy = y + h
cv2.rectangle(frame, (x, y), (end_cordx, end_cordy), color, stroke)
# show the camera with frames
cv2.imshow('frame', frame)
import numpy as np
from cv2 import cv2
img_file_path = 'src/children.jpg'
# 얼굴 검출을 위한 케스케이드 분류기 생성 --- ①
face_cascade = cv2.CascadeClassifier(
'data/haarcascade_frontalface_default.xml')
# 눈 검출을 위한 케스케이드 분류기 생성 ---②
eye_cascade = cv2.CascadeClassifier('data/haarcascade_eye.xml')
# 검출할 이미지 읽고 그레이 스케일로 변환 ---③
img = cv2.imread(img_file_path)
print(img)
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# 얼굴 검출 ---④
faces = face_cascade.detectMultiScale(gray)
# 검출된 얼굴 순회 ---⑤
for (x, y, w, h) in faces:
# 검출된 얼굴에 사각형 표시 ---⑥
cv2.rectangle(img, (x, y), (x + w, y + h), (255, 0, 0), 2)
# 얼굴 영역을 ROI로 설정 ---⑦
roi = gray[y:y + h, x:x + w]
# ROI에서 눈 검출 ---⑧
eyes = eye_cascade.detectMultiScale(roi)
# 검출된 눈에 사각형 표 ---⑨
for (ex, ey, ew, eh) in eyes:
cv2.rectangle(img[y:y + h, x:x + w], (ex, ey), (ex + ew, ey + eh),
(0, 255, 0), 2)
# 결과 출력
cv2.imshow('img', img)
cv2.waitKey(0)
from cv2 import cv2
face_cascade = cv2.CascadeClassifier(
'C://Users/sheetal/Desktop/python_demoProjects/face_detector.xml')
img = cv2.imread('C://Users/sheetal/Desktop/python_demoProjects/dog.jpg')
faces = face_cascade.detectMultiScale(img, 1.1, 4)
for (x, y, w, h) in faces:
cv2.rectangle(img, (x, y), (x + w, y + h), (255, 0, 0), 2)
cv2.imwrite("C://Users/sheetal/Desktop/python_demoProjects/face_detected.png",
img)
print('Successfully saved')
def main():
class NewlineFormatter(argparse.HelpFormatter):
def _split_lines(self, text, width):
return text.splitlines()
parser = argparse.ArgumentParser(
description="Detect and crop faces from an image.",
formatter_class=NewlineFormatter,
)
parser.add_argument(
"image",
nargs="+",
help="path to input image",
)
parser.add_argument(
"--cascade",
default="haarcascade_frontalface_default.xml",
help="face detection cascade to be used by OpenCV",
)
parser.add_argument(
"-o",
"--output",
default="{name}_{i}.png",
help="Output path template, evaluates placehoders: \n\
{path} -> original file path, \n\
{name} -> original file name, \n\
{ext} -> original file extension, \n\
{i} -> index of detected face",
)
parser.add_argument(
"-p",
"--padding",
type=float,
default="0.3",
help="relative space around recognized face (> 0), default=0.3",
)
parser.add_argument(
"-s",
"--size",
type=int,
default="200",
help="export image resolution height / width, default=200",
)
parser.set_defaults(grayscale=False)
parser.add_argument(
"-g",
"--grayscale",
dest="grayscale",
action="store_true",
help="grayscale cropped image",
)
parser.add_argument(
"-v",
"--verbose",
help="increase verbosity (may be applied multiple times)",
action="count",
default=0)
parser.add_argument("-c",
"--color",
default=(255, 255, 255, 0),
type=eval,
help="background color for circular cutout, " +
"BRG(A)-format, default: (255, 255, 255, 0)")
args = parser.parse_args()
logging_level = max(10, logging.WARN - (args.verbose) * 10)
logger.setLevel(logging_level)
logger.debug(f"set logging level to {logging_level}")
cascade_module = os.path.join(os.path.dirname(__file__),
f"haarcascades/{args.cascade}")
if os.path.exists(args.cascade):
logger.info(f"Loading {args.cascade}")
cascade = cv2.CascadeClassifier(args.cascade)
elif os.path.exists(cascade_module):
logger.info(f"Loading {cascade_module}")
cascade = cv2.CascadeClassifier(cascade_module)
else:
logger.fatal(f"cascade could not be loaded, path: {cascade_module}")
sys.exit(1)
for image_path in args.image:
img = cv2.imread(image_path)
logger.info(f"Processing {image_path}, " +
f"resolution: {len(img)}x{len(img[0])}")
# extract variables for output filename generation
output_opts = {}
output_opts["path"] = os.path.dirname(image_path)
output_opts["name"], ext = os.path.splitext(
os.path.basename(image_path))
output_opts["ext"] = ext[1:]
# extract faces by their matched bounding boxes
faces = extract_faces(img, cascade, spacing=args.padding)
logging.info(f"Found {len(faces)} faces")
for i, face in enumerate(faces):
masked = circle_mask(face, args.color, args.size)
# format output path
output_opts["i"] = i
output_path = args.output.format(**output_opts)
logger.info(
f"Exporting {output_path}, grayscale: {args.grayscale}")
export(masked, output_path, args.grayscale)
#we will use opencv's library to detect the faces. If you want to detect the custom object or you want to build something custom, use this tutorial: https://www.youtube.com/watch?v=dZ4itBvIjVY
from cv2 import cv2
faceCascade = cv2.CascadeClassifier("Resources/haarcascade_frontalface_default.xml")
img = cv2.imread('Resources/khabib.jpg')
imgGray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
#find the faces of image using face cascade
faces = faceCascade.detectMultiScale(imgGray,1.1,4)
#bounding box around faces
for (x,y,w,h) in faces:
cv2.rectangle(img,(x,y),(x+w,y+h),(255,0,0),2)
cv2.imshow("Result", img)
cv2.waitKey(0)
from cv2 import cv2
import os
from datetime import datetime
from imutils.video import VideoStream
import face_recognition
import imutils
import pickle
import time
import cv2
from imutils import paths
detector = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
def screen(data_obj):
while (data_obj.get_mode()):
if (data_obj.get_screen()):
frame = cv2.imread("resim.jpg")
s = data_obj.get_data()
cv2.putText(frame, "Yeni kayit yapmak icin 'Yeni'", (170, 150),
cv2.FONT_ITALIC, 1, (255, 255, 255), 2)
cv2.putText(frame, "Cihazi baslatmak icin 'baslat'", (170, 200),
cv2.FONT_ITALIC, 1, (255, 255, 255), 2)
cv2.putText(frame, "diye seslenebilirsiniz", (220, 250),
cv2.FONT_ITALIC, 1, (255, 255, 255), 2)
cv2.putText(frame, "{}".format(s[0]), (220, 300), cv2.FONT_ITALIC,
1, (255, 255, 255), 2)
cv2.putText(frame, "{}".format(s[1]), (170, 350), cv2.FONT_ITALIC,
1, (255, 255, 255), 2)
cv2.imshow("Frame", frame)
from cv2 import cv2
import numpy as np
# Load the cascade file
cascade = cv2.CascadeClassifier('nose.xml')
# Load the webcamera
cap = cv2.VideoCapture(0)
# Capture frame (image) continuously using infinite loop
while True:
# read func will capture a frame
ret, frame = cap.read()
# turn the image to grayscale
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
# use detectmultiscale func to detect the nose which returns nose coordinates
rects = cascade.detectMultiScale(gray, 1.7, 11)
# draw the recctangle on the frame
# print(rects)
for (x, y, w, h) in rects:
y = int(y - 0.15 * h)
cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 255, 0), 3)
cv2.putText(frame, "No Mask", (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 0.7,
(0, 0, 255), 2)
break
else:
cv2.putText(frame, "Detected Mask", (10, 30), cv2.FONT_HERSHEY_SIMPLEX,
0.7, (0, 0, 255), 2)
def screen(data_obj):
while (data_obj.get_mode()):
if (data_obj.get_screen()):
frame = cv2.imread("resim.jpg")
s = data_obj.get_data()
cv2.putText(frame, "Yeni kayit yapmak icin 'Yeni'", (170, 150),
cv2.FONT_ITALIC, 1, (255, 255, 255), 2)
cv2.putText(frame, "Cihazi baslatmak icin 'baslat'", (170, 200),
cv2.FONT_ITALIC, 1, (255, 255, 255), 2)
cv2.putText(frame, "diye seslenebilirsiniz", (220, 250),
cv2.FONT_ITALIC, 1, (255, 255, 255), 2)
cv2.putText(frame, "{}".format(s[0]), (220, 300), cv2.FONT_ITALIC,
1, (255, 255, 255), 2)
cv2.putText(frame, "{}".format(s[1]), (170, 350), cv2.FONT_ITALIC,
1, (255, 255, 255), 2)
cv2.imshow("Frame", frame)
else:
detector = cv2.CascadeClassifier(
'haarcascade_frontalface_default.xml')
total = 0
cap = cv2.VideoCapture(0)
datadir = 'dataset'
name = data_obj.get_name()
if os.path.isdir('dataset'):
pass
else:
os.mkdir(datadir)
path1 = '{}'.format(name)
path = os.path.join(datadir, path1)
os.mkdir(path)
a = datetime.now()
while (True):
ret, frame = cap.read()
orig = frame.copy()
frame = imutils.resize(frame, width=800)
rects = detector.detectMultiScale(cv2.cvtColor(
frame, cv2.COLOR_BGR2GRAY),
scaleFactor=1.1,
minNeighbors=5,
minSize=(30, 30))
for (x, y, w, h) in rects:
cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 255, 0),
2)
cv2.imshow("Frame", frame)
b = datetime.now()
if ((b - a).seconds >= 2):
a = b
p = os.path.sep.join([path, "{}.png".format(str(total))])
cv2.imwrite(p, orig)
if total == 10:
break
total += 1
cap.release()
data_obj.set_screen(True)
key = cv2.waitKey(1) & 0xFF
if key == ord("q"):
break
if (not data_obj.get_mode()):
imagePaths = list(paths.list_images("dataset"))
knownEncodings = []
knownNames = []
for (i, imagePath) in enumerate(imagePaths):
name = imagePath.split(os.path.sep)[-2]
image = cv2.imread(imagePath)
rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
boxes = face_recognition.face_locations(rgb, model="hog")
encodings = face_recognition.face_encodings(rgb, boxes)
for encoding in encodings:
knownEncodings.append(encoding)
knownNames.append(name)
data = {"encodings": knownEncodings, "names": knownNames}
f = open("encodings.pickle", "wb")
f.write(pickle.dumps(data))
f.close()
data = pickle.loads(open("encodings.pickle", "rb").read())
detector = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
vs = VideoStream(src=0).start()
time.sleep(2.0)
while True:
frame = vs.read()
frame = imutils.resize(frame, width=800)
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
rects = detector.detectMultiScale(gray,
scaleFactor=1.1,
minNeighbors=5,
minSize=(30, 30),
flags=cv2.CASCADE_SCALE_IMAGE)
boxes = [((int)(y), (int)(x + w), (int)(y + h), (int)(x))
for (x, y, w, h) in rects]
encodings = face_recognition.face_encodings(rgb, boxes)
names = []
for encoding in encodings:
matches = face_recognition.compare_faces(
data["encodings"], encoding)
name = "Bilinmeyen"
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)
for ((top, right, bottom, left), name) in zip(boxes, names):
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)
cv2.imshow("Frame", frame)
key = cv2.waitKey(1) & 0xFF
if key == ord("q"):
break
cv2.destroyAllWindows()
import numpy as np
from cv2 import cv2
import sqlite3
import openpyxl
face_cascade = cv2.CascadeClassifier('lib/haarcascade_frontalface_default.xml')
cap = cv2.VideoCapture(0)
rec = cv2.face.LBPHFaceRecognizer_create()
rec.read("trainingdata.yml")
id = 0
workbook = openpyxl.load_workbook('Diemdanh.xlsx')
ws = workbook.worksheets[0]
# set text style
fontface = cv2.FONT_HERSHEY_COMPLEX_SMALL
fontscale = 1
fontcolor = (255, 23, 252)
def getProfile(id):
conn = sqlite3.connect("FaceBase.db")
cmd = "SELECT * FROM People WHERE ID=" + str(id)
cursor = conn.execute(cmd)
profile = None
for row in cursor:
profile = row
conn.close()
return profile
from cv2 import cv2
import numpy as np
cap = cv2.VideoCapture('G:\\Python\\I_Processing\\footage.mp4')
human_cascade = cv2.CascadeClassifier('haarcascade_fullbody.xml')
while True:
cord = []
ret, frame = cap.read()
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
human = human_cascade.detectMultiScale(gray, 1.1, 4)
for (x, y, w, h) in human:
cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 0, 220), 3)
cord.append([x, y, w, h])
cv2.imshow('video', frame)
if cv2.waitKey(25) & 0xFF == ord('q'):
break
print(cord)
cap.release()
cv2.destroyAllWindows()
from cv2 import cv2
import numpy as np
from sklearn.neighbors import KNeighborsClassifier
data = np.load("face_data.npy")
print(data.shape, data.dtype)
X = data[:, 1:].astype(int)
y = data[:, 0]
model = KNeighborsClassifier()
model.fit(X, y)
cap = cv2.VideoCapture(cv2.CAP_DSHOW)
detector = cv2.CascadeClassifier(
"./Datasets/haarcascade_frontalface_default.xml")
while True:
ret, frame = cap.read()
if ret:
faces = detector.detectMultiScale(frame)
for face in faces:
x, y, w, h = face
cut = frame[y:y + h, x:x + w]
fix = cv2.resize(cut, (100, 100))
gray = cv2.cvtColor(fix, cv2.COLOR_BGR2GRAY)
# -*- coding: utf-8 -*-
"""
Created on Thu Jun 4 13:38:33 2020
@author: Vishal
"""
# Importing the libraries
from cv2 import cv2
import os
# os.environ["OPENCV_VIDEOIO_DEBUG"] = '1'
# Loading the cascades
face_cascade = cv2.CascadeClassifier('Face_Recognition/haarcascade/haarcascade_frontalface_default.xml')
eye_cascade = cv2.CascadeClassifier('Face_Recognition/haarcascade/haarcascade_eye.xml')
smile_cascade = cv2.CascadeClassifier('Face_Recognition/haarcascade/haarcascade_smile.xml')
# Detect the face and eye
def detect(gray, frame):
# get the face from gray image
faces = face_cascade.detectMultiScale(image=gray, scaleFactor=1.3, minNeighbors=5)
for (x,y,w,h) in faces:
# create the rectangle box on colored image
cv2.rectangle(frame, (x,y), (x+w,y+h), (0,0,255), 2)
# take the boundaries of face in gray and colo image
roi_gray = gray[y:y+h, x:x+w]
roi_color = frame[y:y+h, x:x+w]
# get the face from roi_gray image