def addn(save):
ans = str(speech("Yes or No"))
if (ans == "yes" or ans == "Yes"):
saveface(save)
elif (ans == "no" or ans == "No"):
ignoreface()
else:
generate_sound("Could not understand your response Answer again")
addn(save)
def speech(abc):
# obtain audio from the microphone
r = sr.Recognizer()
with sr.Microphone() as source:
print("Pls say something....")
generate_sound(abc)
audio = r.listen(source)
# recognize speech
try:
print("Google Audio:" + r.recognize_google(audio))
return (r.recognize_google(audio))
# print("Sphinx:" + r.recognize_sphinx(audio))
except sr.UnknownValueError:
generate_sound("Could not understand your response Speak again")
speech(abc)
except sr.RequestError as e:
print("error: {0}".format(e))
generate_sound("Connection Error")
while True:
ret, frame = cap.read()
facedetect = cv.CascadeClassifier(r'haarcascade_frontalface_default.xml')
if ret:
# font = cv.FONT_HERSHEY_SIMPLEX
cv.imshow("Video", frame)
if cv.waitKey(5) == ord('p'):
cv.imwrite('./test.jpg', frame)
final_caption = p_part.generate_caption(
'./test.jpg') # create caption
final_caption = modcap(final_caption) # remove tags
print(final_caption)
generate_sound(final_caption) # convert to audio
if cv.waitKey(5) == ord('f'):
gray = cv.cvtColor(frame, cv.COLOR_BGR2GRAY)
faces = facedetect.detectMultiScale(gray, 1.3, 5)
cv.imwrite('./test.jpg', frame)
try:
for x, y, w, h in faces:
#cv2.imwrite("dset//User."+str(user)+"."+str(sample)+".jpg",gray[y:y+h,x:x+w])
save = frame[y:y+h, x:x+w]
cv.imwrite('./test.jpg', save)
dis, name = f_part.who_is_it('./test.jpg')
print(str(dis)+","+name)
temp = face_found_cap(name)
generate_sound(temp)
if(name == 'unknown'):
def ignoreface():
generate_sound("Not saved")
while True:
ret, frame = cap.read()
facedetect = cv.CascadeClassifier(r'haarcascade_frontalface_default.xml')
if ret:
# font = cv.FONT_HERSHEY_SIMPLEX
cv.imshow("Video", frame)
if cv.waitKey(1) == ord('p'):
cv.imwrite('./test.jpg', frame)
final_caption = p_part.generate_caption(
'./test.jpg') # create caption
final_caption = modcap(final_caption) # remove tags
print(final_caption)
generate_sound(final_caption) # convert to audio
if cv.waitKey(1) == ord('f'):
gray = cv.cvtColor(frame, cv.COLOR_BGR2GRAY)
faces = facedetect.detectMultiScale(gray, 1.3, 5)
cv.imwrite('./test.jpg', frame)
known_detected = 0
unknown_detected = 0
known_face_list = []
known_face_dist = []
try:
for x, y, w, h in faces:
#cv2.imwrite("dset//User."+str(user)+"."+str(sample)+".jpg",gray[y:y+h,x:x+w])
save = frame[y:y + h, x:x + w]
cv.imwrite('./test.jpg', save)
dis, name = f_part.who_is_it('./test.jpg')