def verification(self):
ap = argparse.ArgumentParser()
ap.add_argument("-i","--image", required=True, help="path to input image")
args=vars(ap.parse_args())
print("[INFO] starting video stream ...")
vs = VideoSteam(usePiCamera=True).start()
time.sleep(60.0)
found =set()
while True:
frame=vs.read()
frame=imutils.resize(frame,width=400)
barcodes=pyzbar.decode(frame)
for barcode in barcodes:
(x,y,w,h)= barcode.rect
cv2.retangle(image,(x,y),(x+w,y+h),(0,0,255),2)
barcodeData = barcode.data.decode("utf-8")
barcodeType = barcode.type
text= "{} ({})".format(barcodeData, barcodeType)
cv2.putText(image,text,(x,y-10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0,0,255),2)
if barcodeData not in found:
return None
else:
found.intersection(barcodeData)
def face_detect(path, file_name):
img = cv2.imread(path)
cascade = cv2.CascadeClassifier('/root/Semi/kyberi/body10/haarcascade_upperbody.xml')
rects = cascade.detectMultiScale(img, 1.3, 4, cv2.cv.CV_HAAR_SCALE_IMAGE, (20,20))
if len(rects) == 0:
return False
rects[:, 2:] += rects[:, :2]
for x1, y1, x2, y2 in rects:
cv2.retangle(img, (x1, y1), (x2, y2), (127, 255,0), 2)
cv2.imwrite('%s/%s-%s' % (FACES_DIR, PCAP, file_name), img)
return True
def detect(grey, orig_img):
faces = face_cascade.detectMultiScale(grey, 1.1, 5)
for (x, y, w, h) in faces:
cv2.retangle(orig_img, (x, y), (x + w, y + h), (255, 0, 0), 2)
roi_grey = grey[y:y + h, x:x + w]
roi_color = orig_img[y:y + h, x:x + w]
smiles = smile_cascade.detectMultiScale(roi_grey, 1.7, 22)
for (sx, sy, sw, sh) in smiles:
cv2.rectangle(roi_color, (sx, sy), (sx + sw, sy + sh), (0, 255, 0))
eye = eye_cascade.detectMultiscale(roi_grey, 1.1, 22)
for (ex, ey, ew, eh) in eye:
cv2.rectangle(roi_color, (ex, ey), (ex + ew, ey + eh), (0, 255, 0),
2)
return orig_img
def face_detect(path, file_name):
img = cv2.imread(path)
# apply a classifier that is trained in advanced for detecting faces
# in a front-facing orientation
cascade = cv2.CascadeClassifier('/home/bytegirl/Desktop/haarcascade_upperbody.xml')
# returns retangle coordinates that correspnd to where the face
# was detected in the image.
rects = cascade.detectMultiScale(img, 1.3, 4, cv2.cv.CV_HAAR_SCALE_IMAGE, (20,20))
if len(rects) == 0:
return False
rects[:, 2:] += rects[:, :2]
# highlight the faces in the image
# draw a green retangle over the area
for x1, y1, x2, y2 in rects:
cv2.retangle(img, (x1, y1), (x2, y2), (127, 255,0), 2)
# write out the resulting image
cv2.imwrite('%s/%s-%s' % (FACES_DIR, PCAP, file_name), img)
return True
def face_detect(path, file_name):
img = cv2.imread(path)
cascade = cv2.CasecadeClassifier("haarcascade_frontalface_alt.xml")
rects = cascade.detectMultiScale(img, 1.3, 4, cv2.cv.CV_HAAR_SCALE_IMAGE,
(20, 20))
if len(rects) == 0:
return False
rects[:, 2:] += rects[:, :2]
# highlight the faces in the image
for x1, y1, x2, y2 in rects:
cv2.retangle(img, (x1, y1), (x2, y2), (127, 255, 0), 2)
cv2.imwrite("%s/%s-%s" % (faces_directory, pcap_file, file_name), img)
return True
def face_detect(path, file_name):
img = cv2.imread(path)
# apply a classifier that is trained in advanced for detecting faces
# in a front-facing orientation
cascade = cv2.CascadeClassifier(
'/home/bytegirl/Desktop/haarcascade_upperbody.xml')
# returns retangle coordinates that correspnd to where the face
# was detected in the image.
rects = cascade.detectMultiScale(img, 1.3, 4, cv2.cv.CV_HAAR_SCALE_IMAGE,
(20, 20))
if len(rects) == 0:
return False
rects[:, 2:] += rects[:, :2]
# highlight the faces in the image
# draw a green retangle over the area
for x1, y1, x2, y2 in rects:
cv2.retangle(img, (x1, y1), (x2, y2), (127, 255, 0), 2)
# write out the resulting image
cv2.imwrite('%s/%s-%s' % (FACES_DIR, PCAP, file_name), img)
return True
def face_mask_image():
global RGB_image
print('[Info] Loading Face Detector Model...')
proto_Path = os.path.sep.join(['face_detector', 'deploy.prototxt'])
weights_Path = os.path.sep.join(
['face_detection', 'res10_300x300_ssd_iter_140000.caffemodel'])
net = cv2.dnn.readNet(proto_Path, weights_Path)
print('[Info] loading face mask detector model........')
# load the face mask detector model
model = load_model('face_mask_detector.model')
# load image input and grab the image spatial / dimensions
image = cv2.imread('./images/out.jpg')
(h, w) = image.shape[:2]
# construct a blob from the image
blob = cv2.dnn.blobFromImage(image, 1.0, (300, 300), (104.0, 177.0, 123.0))
# pass the blob through the network and get the face user face_detection
print('[Info] computing Face Detection......please wait')
net.setInput(blob)
user_detections = net.forward()
# looping over user_detections
for i in range(0, user_detections.shape[2]):
# probability associated with user_detections
confirm = user_detections[0, 0, i, 2]
# filter weak user_detections by ensuring confirm is greater then min confirm
if confirm > 0.5:
# compute the x, y coordinates
coor_box = user_detections[0, 0, i, 3:7] * np.array([w, h, w, h])
(startX, startY, endX, endY) = coor_box.astype('int')
# ensure the coor_box are with in the dimentions of the frame.
(startX, startY) = (max(0, startX), max(0, startY))
(endX, endY) = (min(w - 1, endX), min(h - 1, endY))
# extract the face ROI, convert , convert iy from BGR to Rgb channel
# and resize it to 224 x224, and preprocess it.
face_change = image[startY:endY, startX:endX]
face_change = cv2.cvtColor(face_change, cv2.COLOR_BGB2RGB)
face_change = cv2.resize(face_change, (224, 224))
face_change = img_to_array(face_change)
face_change = preprocess_input(face_change)
face_change = np.expand_dims(face_change, axis=0)
# pass the face_change through the model to determine if user has mask or not
(with_mask, with_out_mask) = model.predict(face_change)[0]
#determin the class label and color used to draw coor_box retangle output frame
label = "Mask" if with_mask > with_out_mask else "No Mask"
color = (0, 255, 0) if label == "Mask" else (0, 0, 255)
# Probability in label
label = "{}: {:.2f}%".format(label,
max(with_mask, with_out_mask) * 100)
# label retangle output frame
cv2.putText(image, label, (startX, startY - 10),
cv2.FONT_HERSHEY_SIMPLEX, 0.45, color, 2)
cv2.retangle(image, (startX, startY), (endX, endY), color, 2)
RGB_image = cv2.cvrColor(image, cv2.COLOR_B2B2RGB)
#!/usr/bin/env python # coding: utf8 # author: youdi import numpy as np import cv2 img = np.zeros(shape=(512, 512, 3), dtype=np.uint8) cv2.retangle(img, (384, 0), (510, 128), (0, 255, 0), 3)