class SmileDetector:
def __init__(self):
dir_path = os.path.dirname(os.path.abspath(__file__))
self.network = EMR(
os.path.abspath(
os.path.join(dir_path,
"../Models/sentiment_net/sentiment_net")))
self.network.build_network()
self.final_layer = joblib.load(
os.path.abspath(os.path.join(dir_path, "../Models/svm_model.pkl")))
def preprocess_image(self, image):
image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
self.image = cv2.resize(image,
(48, 48), interpolation=cv2.INTER_CUBIC) / 255.
def predict(self):
result = self.network.predict(self.image)
output = self.final_layer.predict(result)
if output:
return False
else:
return True
network = EMR()
network.build_network()
video_capture = cv2.VideoCapture(0)
font = cv2.FONT_HERSHEY_SIMPLEX
feelings_faces = []
for index, emotion in enumerate(EMOTIONS):
feelings_faces.append(cv2.imread('./emojis/' + emotion + '.png', -1))
while True:
# Capture frame-by-frame
ret, frame = video_capture.read()
# Predict result with network
result = network.predict(format_image(frame))
# Write results in frame
if result is not None:
for index, emotion in enumerate(EMOTIONS):
cv2.putText(frame, emotion, (10, index * 20 + 20),
cv2.FONT_HERSHEY_PLAIN, 0.5, (0, 255, 0), 1)
cv2.rectangle(frame, (130, index * 20 + 10),
(130 + int(result[0][index] * 100),
(index + 1) * 20 + 4), (255, 0, 0), -1)
face_image = feelings_faces[np.argmax(result[0])]
for c in range(0, 3):
frame[200:320, 10:130, c] = face_image[:, :, c] * \
(face_image[:, :, 3] / 255.0) + frame[200:320,
'haarcascade_files/haarcascade_frontalface_default.xml')
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
faces = facecasc.detectMultiScale(gray, 1.3, 5)
if not len(faces) > 0:
# do nothing if no face is detected
a = 1
else:
# draw box around faces
for face in faces:
(x, y, w, h) = face
frame = cv2.rectangle(frame, (x, y - 30), (x + w, y + h + 10),
(255, 0, 0), 2)
newimg = frame[y:y + h, x:x + w]
newimg = cv2.resize(newimg, (48, 48),
interpolation=cv2.INTER_CUBIC) / 255.
result = network.predict(newimg)
if result is not None:
result[0][2] -= 0.15
result[0][4] -= 0.15
if result[0][3] > 0.06:
result[0][3] += 0.4
maxindex = np.argmax(result[0])
font = cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(frame, EMOTIONS[maxindex], (x + 5, y - 5), font, 2,
(255, 255, 255), 2, cv2.LINE_AA)
cv2.imshow(
'Video',
cv2.resize(frame, None, fx=2, fy=2, interpolation=cv2.INTER_CUBIC))
if cv2.waitKey(1) & 0xFF == ord('q'):
break
def format_image(image):
"""
Function to format frame
"""
if len(image.shape) > 2 and image.shape[2] == 3:
image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
else:
image = cv2.imdecode(image, cv2.CV_LOAD_IMAGE_GRAYSCALE)
faces = cascade_classifier.detectMultiScale(image, scaleFactor=1.3, minNeighbors=if not len(faces) > 0:
return None
max_area_face=faces[0]
for face in faces:
if face[2] * face[3] > max_area_face[2] * max_area_face[3]:
max_area_face=face
face=max_area_face
image=image[face[1]:(face[1] + face[2]), face[0]:(face[0] + face[3])]
try:
image=cv2.resize(image, (48, 48), interpolation=cv2.INTER_CUBIC) / 255.
except Exception:
print("----->Problem during resize")
return None
return image
network=EMR()
network.build_network()
cap=cv2.VideoCapture(0)
font=cv2.FONT_HERSHEY_SIMPLEX
feelings_faces=[]
for index, emotion in enumerate(EMOTIONS):
feelings_faces.append(cv2.imread('./emojis/' + emotion + '.png', -1))
while True:
ret, frame=cap.read()
facecasc=cv2.CascadeClassifier(
'haarcascade_files/haarcascade_frontalface_default.xml')
gray=cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
faces=facecasc.detectMultiScale(gray, 1.3, 5)
result=network.predict(format_image(frame))
if result is not None:
# write the different emotions and have a bar to indicate probabilities for each class
for index, emotion in enumerate(EMOTIONS): cv2.putText(frame, emotion, (10, index * 20 + 20),
cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 1);
cv2.rectangle(frame, (130, index * 20 + 10), (130 + int(result[0][index] * 100), (index
+ 1) * 20 + 4), (255, 0, 0), -1)
# find the emotion with maximum probability and display it
maxindex=np.argmax(result[0])
font=cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(frame, EMOTIONS[maxindex], (10, 360), font,
2, (255, 255, 255), 2, cv2.LINE_AA)
face_image=feelings_faces[maxindex]
print(face_image[:, :, 3])
for c in range(0, 3):
frame[200:320, 10:130, c]=face_image[:, :, c] * (face_image[:, :, 3] / 255.0) +
frame[200:320, 10:130, c] * (1.0 - face_image[:, :, 3] / 255.0)
if not len(faces) > 0:
# do nothing if no face is detected
a=1
else:
# draw box around face with maximum area
max_area_face=faces[0]
for face in faces:
if face[2] * face[3] > max_area_face[2] * max_area_face[3]:
max_area_face=face
face=max_area_face
(x, y, w, h)=max_area_face
frame=cv2.rectangle(frame, (x, y-50), (x+w, y+h+10), (255, 0, 0), 2)
cv2.imshow('Video', cv2.resize(frame, None, fx=2,
fy=2, interpolation=cv2.INTER_CUBIC))
if cv2.waitKey(1) & 0xFF == ord('q'):
breakcap.release()
cv2.destroyAllWindows()
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
# Detect faces in the image
faces = faceCascade.detectMultiScale(gray,
scaleFactor=1.2,
minNeighbors=5,
minSize=(30, 30)
#flags = cv2.CV_HAAR_SCALE_IMAGE
)
print("Found {0} faces!".format(len(faces)))
# Again find haar cascade to draw bounding box around face
# compute softmax probabilities
result = network.predict(format_image(image))
if result is not None:
# write the different emotions and have a bar to indicate probabilities for each class
for index, emotion in enumerate(EMOTIONS):
cv2.putText(image, emotion, (10, index * 20 + 20),
cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 1)
cv2.rectangle(image, (130, index * 20 + 10),
(130 + int(result[0][index] * 100),
(index + 1) * 20 + 4), (255, 0, 0), -1)
# find the emotion with maximum probability and display it
maxindex = np.argmax(result[0])
font = cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(image, EMOTIONS[maxindex], (10, 360), font, 2,
(255, 255, 255), 2, cv2.LINE_AA)
face_image = feelings_faces[maxindex]