def process_img(img):
global pnet, rnet, onet
minsize = 50 # minimum size of face
detec_threshold = 0.7
threshold = [0.6, 0.7, detec_threshold] # three steps's threshold
factor = 0.709 # scale factor
im_name = img.split('/')[-1].split('.')[0]
input_img = plt.imread(img)
faces, pnts = mtcnn_detect_face.detect_face(input_img, minsize, pnet, rnet,
onet, threshold, factor)
print(faces)
print(pnts)
faces = process_mtcnn_bbox(faces, input_img.shape)
for idx, (x0, y1, x1, y0, conf_score) in enumerate(faces):
det_face_im = input_img[int(x0):int(x1), int(y0):int(y1), :]
# get src/tar landmarks
src_landmarks = get_src_landmarks(x0, x1, y0, y1, pnts, idx)
tar_landmarks = get_tar_landmarks(det_face_im)
# align detected face
aligned_det_face_im = landmarks_match_mtcnn(det_face_im, src_landmarks,
tar_landmarks)
fname = f"./faces/aligned_faces/{im_name}face{str(idx)}.jpg"
plt.imsave(fname, aligned_det_face_im, format="jpg")
fname = f"./faces/raw_faces/{im_name}face{str(idx)}.jpg"
plt.imsave(fname, det_face_im, format="jpg")
'''
def get_faces_bbox(image):
minsize = 20 # minimum size of face
threshold = [0.6, 0.7, detect_threshold] # three steps's threshold
factor = 0.709 # scale factor
video_scaling_factor = 1
resized_image = image
if is_higher_than_1080p(image):
video_scaling_factor = 4
resized_image = cv2.resize(image,
(image.shape[1] // video_scaling_factor,
image.shape[0] // video_scaling_factor))
elif is_higher_than_720p(image):
video_scaling_factor = 3
resized_image = cv2.resize(image,
(image.shape[1] // video_scaling_factor,
image.shape[0] // video_scaling_factor))
elif is_higher_than_480p(image):
video_scaling_factor = 2
resized_image = cv2.resize(image,
(image.shape[1] // video_scaling_factor,
image.shape[0] // video_scaling_factor))
faces, pnts = mtcnn_detect_face.detect_face(resized_image, minsize, pnet, rnet, onet, threshold, factor)
faces = process_mtcnn_bbox(faces, image.shape)
faces = calibrate_coord(faces, video_scaling_factor)
return faces
def process_video(input_img):
global frames, save_interval
global pnet, rnet, onet
minsize = 30 # minimum size of face
detec_threshold = 0.7
threshold = [0.6, 0.7, detec_threshold] # three steps's threshold
factor = 0.709 # scale factor
frames += 1
if frames % save_interval == 0:
faces, pnts = mtcnn_detect_face.detect_face(input_img, minsize, pnet,
rnet, onet, threshold,
factor)
faces = process_mtcnn_bbox(faces, input_img.shape)
for idx, (x0, y1, x1, y0, conf_score) in enumerate(faces):
det_face_im = input_img[int(x0):int(x1), int(y0):int(y1), :]
# get src/tar landmarks
src_landmarks = get_src_landmarks(x0, x1, y0, y1, pnts)
tar_landmarks = get_tar_landmarks(det_face_im)
# align detected face
aligned_det_face_im = landmarks_match_mtcnn(
det_face_im, src_landmarks, tar_landmarks)
fname = f"./faces/aligned_faces/frame{frames}face{str(idx)}.jpg"
#plt.imsave(fname, aligned_det_face_im, format="jpg")
cv2.imwrite(fname, aligned_det_face_im)
fname = f"./faces/raw_faces/frame{frames}face{str(idx)}.jpg"
#plt.imsave(fname, det_face_im, format="jpg")
cv2.imwrite(fname, det_face_im)
bm = np.zeros_like(aligned_det_face_im)
h, w = bm.shape[:2]
bm[int(src_landmarks[0][0] - h / 15):int(src_landmarks[0][0] +
h / 15),
int(src_landmarks[0][1] - w / 8):int(src_landmarks[0][1] +
w / 8), :] = 255
bm[int(src_landmarks[1][0] - h / 15):int(src_landmarks[1][0] +
h / 15),
int(src_landmarks[1][1] - w / 8):int(src_landmarks[1][1] +
w / 8), :] = 255
bm = landmarks_match_mtcnn(bm, src_landmarks, tar_landmarks)
fname = f"./faces/binary_masks_eyes/frame{frames}face{str(idx)}.jpg"
#plt.imsave(fname, bm, format="jpg")
cv2.imwrite(fname, bm)
return np.zeros((3, 3, 3))
def detect_face(self, image, minsize=20, threshold=0.7, factor=0.709, use_auto_downscaling=True, min_face_area=25*25):
if use_auto_downscaling:
image, scale_factor = self.auto_downscale(image)
faces, pnts = mtcnn_detect_face.detect_face(
image, minsize,
self.pnet, self.rnet, self.onet,
[0.6, 0.7, threshold],
factor)
faces = self.process_mtcnn_bbox(faces, image.shape)
faces, pnts = self.remove_small_faces(faces, pnts, min_face_area)
if use_auto_downscaling:
faces = self.calibrate_coord(faces, scale_factor)
pnts = self.calibrate_landmarks(pnts, scale_factor)
return faces, pnts
def extract_face_from_img(img, params):
pnet, rnet, onet = params['pnet'], params['rnet'], params['onet']
minsize = params['minsize']
threshold = params['threshold']
factor = params['factor']
faces, pnts = mtcnn_detect_face.detect_face(img, minsize, pnet, rnet, onet,
threshold, factor)
faces = process_mtcnn_bbox(faces, img.shape)
aligned_list = []
det_faces = []
bm_list = []
for idx, (x0, y1, x1, y0, conf_score) in enumerate(faces):
det_face_im = img[int(x0):int(x1), int(y0):int(y1), :]
# get src/tar landmarks
src_landmarks = get_src_landmarks(x0, x1, y0, y1, pnts)
tar_landmarks = get_tar_landmarks(det_face_im)
# align detected face
aligned_det_face_im = landmarks_match_mtcnn(det_face_im, src_landmarks,
tar_landmarks)
bm = np.zeros_like(aligned_det_face_im)
h, w = bm.shape[:2]
bm[int(src_landmarks[0][0] - h / 15):int(src_landmarks[0][0] + h / 15),
int(src_landmarks[0][1] - w / 8):int(src_landmarks[0][1] +
w / 8), :] = 255
bm[int(src_landmarks[1][0] - h / 15):int(src_landmarks[1][0] + h / 15),
int(src_landmarks[1][1] - w / 8):int(src_landmarks[1][1] +
w / 8), :] = 255
bm = landmarks_match_mtcnn(bm, src_landmarks, tar_landmarks)
aligned_list.append(aligned_det_face_im)
det_faces.append(det_face_im)
bm_list.append(bm)
return aligned_list, det_faces, bm_list
onet = K.function(
[onet.layers['data']],
[onet.layers['conv6-2'], onet.layers['conv6-3'], onet.layers['prob1']])
er_model = emotion_recognition_model('weights/mobilenet_0.4379_0.8605.hdf5')
labels = [
'Surprise', 'Fear', 'Disgust', 'Happiness', 'Sadness', 'Anger', 'Neutral'
]
face_input = np.zeros((1, 128, 128, 3))
cap = cv2.VideoCapture(0)
while True:
ret, img = cap.read()
input_img = img.copy()
faces, pnts = mtcnn_detect_face.detect_face(input_img, pnet, rnet, onet)
faces = process_mtcnn_bbox(faces, input_img.shape)
figure_right = np.zeros((input_img.shape[0], 140, 3), np.uint8)
biggest_face_idx = -1
biggest_area = 0
faces_boxes = []
i = 0
for (y0, x1, y1, x0, conf_score) in faces:
if y0 > 0 and x1 > 0 and y1 > 0 and x0 > 0:
faces_boxes.append((y0, x1, y1, x0))
if biggest_area < (y1 - y0) * (x1 - x0):
biggest_area = (y1 - y0) * (x1 - x0)
biggest_face_idx = i
i += 1
'Surprise', 'Fear', 'Disgust', 'Happiness', 'Sadness', 'Anger', 'Neutral'
]
face_input = np.zeros((1, 128, 128, 3))
t_start = time.time()
fps = 0
scale = 4
cap = cv2.VideoCapture(0)
ret, input_img = cap.read()
height, weight, _ = input_img.shape
while True:
ret, img = cap.read()
input_img = img.copy()
img_small = cv2.resize(input_img, (weight // scale, height // scale))
faces, pnts = mtcnn_detect_face.detect_face(img_small, pnet, rnet, onet)
faces = process_mtcnn_bbox(faces, img_small.shape)
figure_right = np.zeros((input_img.shape[0], 140, 3), np.uint8)
biggest_face_idx = -1
biggest_area = 0
faces_boxes = []
i = 0
for (y0, x1, y1, x0, conf_score) in faces:
if y0 > 0 and x1 > 0 and y1 > 0 and x0 > 0:
faces_boxes.append((y0, x1, y1, x0))
if biggest_area < (y1 - y0) * (x1 - x0):
biggest_area = (y1 - y0) * (x1 - x0)
biggest_face_idx = i
i += 1
