def update_buffer(self):
detection_model_path = './Engine/trained_models/detection_models/haarcascade_frontalface_default.xml'
face_detection = load_detection_model(detection_model_path)
# hyper-parameters for bounding boxes shape
frame_window = 10
emotion_offsets = (20, 40)
emotion_labels = get_labels('fer2013')
# starting lists for calculating modes
emotion_window = []
while True:
if self.VideoStreamer.more():
bgr_image = self.VideoStreamer.read()
# sleep(1/30)
# bgr_image = trim_frame(bgr_image)
gray_image = cv2.cvtColor(bgr_image, cv2.COLOR_BGR2GRAY)
rgb_image = cv2.cvtColor(bgr_image, cv2.COLOR_BGR2RGB)
faces = detect_faces(face_detection, gray_image)
# print(str(faces))
for face_coordinates in faces:
x1, x2, y1, y2 = apply_offsets(face_coordinates,
emotion_offsets)
gray_face = gray_image[y1:y2, x1:x2]
try:
gray_face = cv2.resize(gray_face,
(self.emotion_target_size))
except:
continue
gray_face = preprocess_input(gray_face, True)
gray_face = np.expand_dims(gray_face, 0)
gray_face = np.expand_dims(gray_face, -1)
with self.graph.as_default():
emotion_prediction = self.emotion_classifier.predict(
gray_face)
# print(str(emotion_prediction))
# angry = emotion_prediction[0][0]
# disgust = emotion_prediction[0][1]
# fear = emotion_prediction[0][2]
# happy = emotion_prediction[0][3]
# sad = emotion_prediction[0][4]
# surprise = emotion_prediction[0][5]
# neutral = emotion_prediction[0][6]
# with open('../emotion.txt', 'a') as f:
# f.write('{},{},{},{},{},{},{}\n'.format(angry, disgust, fear, happy, sad, surprise, neutral))
emotion_probability = np.max(emotion_prediction)
emotion_label_arg = np.argmax(emotion_prediction)
emotion_text = emotion_labels[emotion_label_arg]
emotion_window.append(emotion_text)
if len(emotion_window) > frame_window:
emotion_window.pop(1)
try:
emotion_mode = mode(emotion_window)
except:
continue
if emotion_text == 'angry':
color = emotion_probability * np.asarray((255, 0, 0))
elif emotion_text == 'sad':
color = emotion_probability * np.asarray((0, 0, 255))
elif emotion_text == 'happy':
color = emotion_probability * np.asarray((255, 255, 0))
elif emotion_text == 'surprise':
color = emotion_probability * np.asarray((0, 255, 255))
else:
color = emotion_probability * np.asarray((0, 255, 0))
color = color.astype(int)
color = color.tolist()
draw_bounding_box(face_coordinates, rgb_image, color)
draw_text(face_coordinates, rgb_image, emotion_mode, color,
0, -45, 1, 1)
bgr_image = cv2.cvtColor(rgb_image, cv2.COLOR_RGB2BGR)
if not self.Q.full():
self.Q.put(bgr_image)
else:
continue
else:
continue
continue
if emotion_text == 'angry':
color = emotion_probability * np.asarray((186,18,0))
elif emotion_text == 'disgust':
color = emotion_probability * np.asarray((126,105,88))
elif emotion_text == 'fear':
color = emotion_probability * np.asarray((255, 255, 255))
elif emotion_text == 'happy':
color = emotion_probability * np.asarray((255,186,8))
elif emotion_text == 'sad':
color = emotion_probability * np.asarray((45,114,143))
elif emotion_text == 'surprise':
color = emotion_probability * np.asarray((136,73,143))
elif emotion_text == 'neutral':
color = emotion_probability * np.asarray((83,221,108))
color = color.astype(int)
color = color.tolist()
draw_bounding_box(face_coordinates, rgb_image, color)
draw_text(face_coordinates, rgb_image, emotion_mode,
color, 0, -45, 1, 1)
bgr_image = cv2.cvtColor(rgb_image, cv2.COLOR_RGB2BGR)
cv2.imshow('window_frame', bgr_image)
if cv2.waitKey(1) & 0xFF == ord('q'):
print("end")
break
def update_buffer(self):
detection_model_path = './Engine/trained_models/detection_models/haarcascade_frontalface_default.xml'
face_detection = load_detection_model(detection_model_path)
# hyper-parameters for bounding boxes shape
frame_window = 10
emotion_offsets = (20, 40)
emotion_labels = get_labels('fer2013')
# starting lists for calculating modes
emotion_window = []
cv2.namedWindow('image', cv2.WINDOW_NORMAL)
while True:
if self.VStreamer.more():
bgr_image = self.VStreamer.read()
# sleep(1/30)
# bgr_image = trim_frame(bgr_image)
gray_image = cv2.cvtColor(bgr_image, cv2.COLOR_BGR2GRAY)
rgb_image = cv2.cvtColor(bgr_image, cv2.COLOR_BGR2RGB)
faces = detect_faces(face_detection, gray_image)
# print(str(faces))
for face_coordinates in faces:
x1, x2, y1, y2 = apply_offsets(face_coordinates,
emotion_offsets)
gray_face = gray_image[y1:y2, x1:x2]
try:
gray_face = cv2.resize(gray_face,
(self.emotion_target_size))
except:
continue
gray_face = preprocess_input(gray_face, True)
gray_face = np.expand_dims(gray_face, 0)
gray_face = np.expand_dims(gray_face, -1)
with self.graph.as_default():
emotion_prediction = self.emotion_classifier.predict(
gray_face)
percentage = np.amax(emotion_prediction)
emotion_label_arg = np.argmax(emotion_prediction)
emotion_text = emotion_labels[emotion_label_arg]
draw_bounding_box(face_coordinates, rgb_image,
percentage * np.asarray((83, 221, 108)))
cv2.imshow('image', rgb_image)
cv2.waitKey(1)
if not self.Q.full():
self.Q.put([emotion_text, percentage])
else:
continue
else:
continue