I am trying to find a speaker from a webcam using facial land marks which i can get using the face_recognition library. I am successful in getting the month top lip and bottom lip points.
I want to calculate the distance b/w these points and according to distance may be we can say person is speaking or not. What i had done so far now.
import face_recognition
import cv2
import math
video_capture = cv2.VideoCapture(0)
while True:
# Grab a single frame of video
ret, frame = video_capture.read()
face_landmarks = face_recognition.face_landmarks(frame)
try:
p1=face_landmarks[0]['top_lip']
p2=face_landmarks[0]['bottom_lip']
x1,y1=p1[9]
x3,y3=p1[8]
x4,y4=p1[10]
x2,y2=p2[9]
x5,y5=p2[8]
x6,y6=p2[10]
dist = math.sqrt(((x2+x5+x6) - (x1+x3+x4)) ** 2 + ((y2+y5+y6) - (y1+y3+y4)) ** 2)
print(dist)
image = cv2.circle(frame, p1[8], 1, (255, 255, 255, 0), 2)
image = cv2.circle(frame, p1[9], 1, (255, 255, 255, 0), 2)
image = cv2.circle(frame, p1[10], 1, (255, 255, 255, 0), 2)
image = cv2.circle(frame, p2[8], 1, (255, 255, 255, 0), 2)
image = cv2.circle(frame, p2[9], 1, (255, 255, 255, 0), 2)
image = cv2.circle(frame, p2[10], 1, (255, 255, 255, 0), 2)
# # cv2.clipLine(frame, p1, p2,(255,255,255,0), thickness=2)
# for p1t in p1:
# image = cv2.circle(frame, p1t, 1, (255,255,255,0), 2)
# for p1b in p2:
# image = cv2.circle(frame, p1b, 1, (255, 255, 255, 0), 2)
cv2.namedWindow('Video', cv2.WINDOW_NORMAL)
cv2.imshow('Video', frame)
except Exception as e:
raise(e)
# Hit 'q' on the keyboard to quit!
if cv2.waitKey(1) & 0xFF == ord('q'):
break
video_capture.release()
cv2.destroyAllWindows()
but the distance which i had calculated is varying even if person don't speak.If anyone has idea that how i can detect speaker using month lands marks then please let me know. Thanks
