def image_deep_alignment(img, transform_kind="crop"):
# convert image to np array
img = np.array(img)
# cv2 image color conversion
img = cv2.cvtColor(img, cv2.COLOR_RGB2BGR)
# initialize detector
face_detector = MTCNN()
face_detector.select_largest = True
# detect landmark points
detections, probs, landmarks = face_detector.detect(img, landmarks=True)
transformed = img
if detections is not None:
x, y, x2, y2 = int(detections[0][0]), int(detections[0][1]), int(
detections[0][2]), int(detections[0][3])
print(x, y, x2, y2)
left_eye = landmarks[0][0]
right_eye = landmarks[0][1]
nose = landmarks[0][4]
h = img.shape[0]
w = img.shape[1]
if transform_kind == FaceAlignTransform.ROTATION:
rotation = get_rotation_matrix(left_eye, right_eye)
#translation = get_translation_matrix(left_eye, w, h)
#translated = cv2.warpAffine(img, translation, img.shape[:2], flags=cv2.INTER_CUBIC)
transformed = cv2.warpAffine(img,
rotation,
img.shape[:2],
flags=cv2.INTER_CUBIC)
elif transform_kind == FaceAlignTransform.AFFINE:
matrix = get_affine_transform_matrix(left_eye, right_eye, nose,
LEFT_EYE_POS(w, h),
RIGHT_EYE_POS(w, h),
NOSE_POS(w, h))
transformed = cv2.warpAffine(img,
matrix,
img.shape[:2],
flags=cv2.INTER_CUBIC)
elif transform_kind == "crop":
y = y - int((y2 - y) * 1 / 3)
if y < 0:
y = 0
y2 = y2 + int((y2 - y) * 1 / 3)
if y2 > h:
y2 = h - 1
x = x - int((x2 - x) * 1 / 3)
if x < 0:
x = 0
x2 = x2 + int((x2 - x) * 1 / 3)
if x2 > w:
x2 = w - 1
return Image.fromarray(
cv2.cvtColor(img[y:y2, x:x2, :], cv2.COLOR_BGR2RGB))
transformed = cv2.cvtColor(transformed, cv2.COLOR_BGR2RGB)
return Image.fromarray(transformed)
def base64arr_to_tensor(frames):
model = model_init()
face_detector = MTCNN()
face_detector.select_largest = True
tensor_arr = []
for frame in frames:
# convert to PIL image
base64img = base64.b64decode(frame)
buf = io.BytesIO(base64img)
img = Image.open(buf).convert('RGB')
img = np.array(img)
# extract face
detections, probs = face_detector.detect(img)
if detections is not None:
x, y, x2, y2 = int(detections[0][0]), int(detections[0][1]), int(
detections[0][2]), int(detections[0][3])
img = Image.fromarray(img[y:y2, x:x2, :])
# resize face
img = resize(img, model.input_size)
# save sample
img.save("last_image.jpg")
transform = transforms.Compose([
transforms.ToTensor(),
transforms.Resize((model.input_size, model.input_size))
])
tensor_arr.append(transform(img))
return torch.stack(tensor_arr)
def set_mtcnn(mtcnn, all, largest, post=False, factor=0.6, min=20):
if type(mtcnn)!=MTCNN: mtcnn = MTCNN()
mtcnn.keep_all = all; mtcnn.post_process = post; mtcnn.factor = factor
mtcnn.select_largest = largest; mtcnn.min_face_size = min; return mtcnn
def image_deep_alignment(img,
transform_kind="crop",
precomputed_detection=None,
precomputed_landmarks=None,
compute_landmarks=True):
# convert image to np array
img = np.array(img)
detections = None
landmarks = None
# compute bounding box and landmarks
if precomputed_detection is None or precomputed_landmarks is None:
device = 'cuda' if torch.cuda.is_available() else 'cpu'
# initialize detector
face_detector = MTCNN(device=device)
face_detector.select_largest = True
detections, probs, landmarks = None, None, None
# detect landmark points
if not compute_landmarks:
detections, probs = face_detector.detect(img, landmarks=False)
else:
detections, probs, landmarks = face_detector.detect(img,
landmarks=True)
else:
detections = precomputed_detection
landmarks = precomputed_landmarks
transformed = img
if detections is not None:
x, y, x2, y2 = int(detections[0][0]), int(detections[0][1]), int(
detections[0][2]), int(detections[0][3])
h = img.shape[0]
w = img.shape[1]
# rotation transformation
if transform_kind == FaceAlignTransform.ROTATION:
left_eye = landmarks[0][0]
right_eye = landmarks[0][1]
nose = landmarks[0][4]
rotation = get_rotation_matrix(left_eye, right_eye)
transformed = cv2.warpAffine(img,
rotation,
img.shape[:2],
flags=cv2.INTER_CUBIC)
# crop the bounding boxes and expand the box by a factor of 1/3
elif transform_kind == "crop":
y = y - int((y2 - y) * 1 / 3)
if y < 0:
y = 0
y2 = y2 + int((y2 - y) * 1 / 3)
if y2 > h:
y2 = h - 1
x = x - int((x2 - x) * 1 / 3)
if x < 0:
x = 0
x2 = x2 + int((x2 - x) * 1 / 3)
if x2 > w:
x2 = w - 1
return Image.fromarray(img[y:y2, x:x2, :]), detections, landmarks
return Image.fromarray(transformed), detections, landmarks
