def display_list_recognized_faces():
list_recognized_faces.clear()
recognized_faces = FaceRecog.get_recognized_faces()
for item in recognized_faces:
list_recognized_faces.addItem(item)
repaint_list(list_recognized_faces)
def faceIdentification():
#speaker("Start face identification system")
face_recog = FaceRecog.FaceRecognition()
print(face_recog.known_face_names)
name = "Unknown"
for i in range(3):
print(i)
name, frame = face_recog.get_frame()
print("took photo")
if name != "Unknown":
greeting = "Hello " + name
speaker(greeting)
break
# take photo interval = 3 sec
time.sleep(3)
# show the frame
cv2.imshow("Frame", frame)
key = cv2.waitKey(1) & 0xFF
print(name)
if i == 2:
#speaker("Get out!")
print("Get out!")
cv2.imwrite('stranger.jpg',
frame,
params=[cv2.IMWRITE_PNG_COMPRESSION, 0])
# +++++++++++MESSAGE++++++++++++++
# do a bit of cleanup
cv2.destroyAllWindows()
def pb_recognize_faces_clicked():
# run selected recognition method
recognition_method = cb_recognition_method.currentText()
number_of_neighbors = int(recognition_method[:1])
recognize_image = FaceRecog.run_knn(upload_image_path, number_of_neighbors)
# display image with detected objects
recognize_image.save("temp files/tempRecog.jpg")
display_image_faces("temp files/tempRecog.jpg")
# display results
display_recognition_time()
display_number_of_faces_recognized()
display_list_recognized_faces()
def display_recognition_time():
recognition_time = str(round(FaceRecog.get_recognition_time(), 5))
l_face_recognition_time.setText(recognition_time)
l_face_recognition_time.repaint()
def display_number_of_faces_recognized():
number_of_faces_recognized = str(
FaceRecog.get_number_of_faces_recognized())
l_faces_recognized.setText(number_of_faces_recognized)
l_faces_recognized.repaint()
import CascadeDetector
import FrameGenerator
from PIL import Image
from imutils.object_detection import non_max_suppression
from imutils import paths
import imutils
import numpy as np
import os, sys, time
#import ty
import json
print("Hello")
fn_haar = 'FACE'
fn_dir = 'database'
rec = FaceRecog.FaceRecog(recogtype="OD_LBPH_FACE")
rec.initTrainer(location=fn_dir)
(image, lables, names, id) = ([], [], {}, 0)
print("Training ......")
image, lables, names, id = rec.train()
hog = cv2.HOGDescriptor()
hog.setSVMDetector(cv2.HOGDescriptor_getDefaultPeopleDetector())
app = Flask(__name__)
def pydetect_vid(name):
size = 4
fn_haar = 'trained/haarcascade_frontalface_default.xml'
fn_dir = 'database'
def frecog():
content = request.get_json()
img_data = content['ImageBLOB']
imgdata = base64.b64decode(img_data)
filename = 'image2.png'
with open(filename, 'wb') as f:
f.write(imgdata)
#name=ty.m()
im = cv2.imread("image2.png")
im = cv2.flip(im, 1, 0)
size = 4
fn_haar = 'FACE'
fn_dir = 'database'
rec = FaceRecog.FaceRecog(recogtype="OD_LBPH_FACE")
rec.initTrainer(location=fn_dir)
print("Training ......")
image, lables, names, id = rec.train()
#print(names)
(im_width, im_height) = (224, 184)
det = CascadeDetector.CascadeDetector()
det.setTrainedDataId(fn_haar)
det.setTrainedDataLocation()
#print(det.getTrainedDataLocation())
det.initDetector()
det.setScaleFactor(1.3)
det.setMinNeighbours(5)
gray = det.gray(im)
#cv2.imwrite("gray.jpg",gray)
faces = det.detect(gray)
print(len(faces))
send = ""
for (x, y, w, h) in faces:
cv2.rectangle(im, (x, y), (x + w, y + h), (255, 0, 0), 2)
face = gray[y:y + h, x:x + w]
cv2.rectangle(im, (x, y), (x + w, y + h), (0, 255, 0), 3)
pred, l, conf = rec.predict(face, im_width, im_height)
print(pred, conf)
#print ("pred",prediction)
if conf < 90:
send = send + names[pred] + " "
cv2.putText(im, '%s - %.0f' % (names[pred], pred),
(x - 10, y - 10), cv2.FONT_HERSHEY_PLAIN, 1,
(0, 255, 0))
else:
send = send + "Unrecognized face" + " "
cv2.putText(im, 'not recognized', (x - 10, y - 10),
cv2.FONT_HERSHEY_PLAIN, 1, (0, 0, 255))
#cv2.imshow('OpenCV', im)
#key = cv2.waitKey(10000)
#webcam.release()
#cv2.destroyAllWindows()
#server_response = [{'aaa', "lmao"}]
#josn_obj = demjson.encode(server_response)
send = send + " Detected"
print(send)
data2 = {"name": send}
#json_data = json.dumps(data2)
return jsonify(data2)