Python dlib.rectangle方法代碼示例

# 需要導入模塊: import dlib [as 別名]
# 或者: from dlib import rectangle [as 別名]
def getLargestFaceBoundingBox(self, rgbImg, skipMulti=False):
        """
        Find the largest face bounding box in an image.

        :param rgbImg: RGB image to process. Shape: (height, width, 3)
        :type rgbImg: numpy.ndarray
        :param skipMulti: Skip image if more than one face detected.
        :type skipMulti: bool
        :return: The largest face bounding box in an image, or None.
        :rtype: dlib.rectangle
        """
        assert rgbImg is not None

        faces = self.getAllFaceBoundingBoxes(rgbImg)
        if (not skipMulti and len(faces) > 0) or len(faces) == 1:
            return max(faces, key=lambda rect: rect.width() * rect.height())
        else:
            return None 

# 需要導入模塊: import dlib [as 別名]
# 或者: from dlib import rectangle [as 別名]
def findLandmarks(self, rgbImg, bb):
        """
        Find the landmarks of a face.

        :param rgbImg: RGB image to process. Shape: (height, width, 3)
        :type rgbImg: numpy.ndarray
        :param bb: Bounding box around the face to find landmarks for.
        :type bb: dlib.rectangle
        :return: Detected landmark locations.
        :rtype: list of (x,y) tuples
        """
        assert rgbImg is not None
        assert bb is not None

        points = self.predictor(rgbImg, bb)
        #return list(map(lambda p: (p.x, p.y), points.parts()))
        return [(p.x, p.y) for p in points.parts()]

    #pylint: disable=dangerous-default-value 

# 需要導入模塊: import dlib [as 別名]
# 或者: from dlib import rectangle [as 別名]
def getLargestFaceBoundingBox(self, rgbImg, skipMulti=False):
        """
        Find the largest face bounding box in an image.
        :param rgbImg: RGB image to process. Shape: (height, width, 3)
        :type rgbImg: numpy.ndarray
        :param skipMulti: Skip image if more than one face detected.
        :type skipMulti: bool
        :return: The largest face bounding box in an image, or None.
        :rtype: dlib.rectangle
        """
        assert rgbImg is not None

        faces = self.getAllFaceBoundingBoxes(rgbImg)
        if (not skipMulti and len(faces) > 0) or len(faces) == 1:
            return max(faces, key=lambda rect: rect.width() * rect.height())
        else:
            return None 

# 需要導入模塊: import dlib [as 別名]
# 或者: from dlib import rectangle [as 別名]
def getLargestFaceBoundingBox(self, rgbImg):
        """
        Find the largest face bounding box in an image.

        :param rgbImg: RGB image to process. Shape: (height, width, 3)
        :type rgbImg: numpy.ndarray
        :return: The largest face bounding box in an image, or None.
        :rtype: dlib.rectangle
        """
        assert rgbImg is not None

        faces = self.getAllFaceBoundingBoxes(rgbImg)
        if len(faces) > 0:
            return max(faces, key=lambda rect: rect.width() * rect.height())
        else:
            return None 

# 需要導入模塊: import dlib [as 別名]
# 或者: from dlib import rectangle [as 別名]
def findLandmarks(self, rgbImg, bb):
        """
        Find the landmarks of a face.

        :param rgbImg: RGB image to process. Shape: (height, width, 3)
        :type rgbImg: numpy.ndarray
        :param bb: Bounding box around the face to find landmarks for.
        :type bb: dlib.rectangle
        :return: Detected landmark locations.
        :rtype: list of (x,y) tuples
        """
        assert rgbImg is not None
        assert bb is not None

        points = self.predictor(rgbImg, bb)
        return list(map(lambda p: (p.x, p.y), points.parts())) 

# 需要導入模塊: import dlib [as 別名]
# 或者: from dlib import rectangle [as 別名]
def predict(image, model, shape_predictor=None):
    # get landmarks
    if NETWORK.use_landmarks or NETWORK.use_hog_and_landmarks or NETWORK.use_hog_sliding_window_and_landmarks:
        face_rects = [dlib.rectangle(left=0, top=0, right=NETWORK.input_size, bottom=NETWORK.input_size)]
        face_landmarks = np.array([get_landmarks(image, face_rects, shape_predictor)])
        features = face_landmarks
        if NETWORK.use_hog_sliding_window_and_landmarks: 
            hog_features = sliding_hog_windows(image)
            hog_features = np.asarray(hog_features)
            face_landmarks = face_landmarks.flatten()
            features = np.concatenate((face_landmarks, hog_features))
        else:
            hog_features, _ = hog(image, orientations=8, pixels_per_cell=(16, 16),
                                    cells_per_block=(1, 1), visualise=True)
            hog_features = np.asarray(hog_features)
            face_landmarks = face_landmarks.flatten()
            features = np.concatenate((face_landmarks, hog_features))
        tensor_image = image.reshape([-1, NETWORK.input_size, NETWORK.input_size, 1])
        predicted_label = model.predict([tensor_image, features.reshape((1, -1))])
        return get_emotion(predicted_label[0])
    else:
        tensor_image = image.reshape([-1, NETWORK.input_size, NETWORK.input_size, 1])
        predicted_label = model.predict(tensor_image)
        return get_emotion(predicted_label[0])
    return None 

# 需要導入模塊: import dlib [as 別名]
# 或者: from dlib import rectangle [as 別名]
def getLandmarks(im):
    imSmall = cv2.resize(im, None, 
                            fx = 1.0/FACE_DOWNSAMPLE_RATIO, 
                            fy = 1.0/FACE_DOWNSAMPLE_RATIO, 
                            interpolation = cv2.INTER_LINEAR)

    rects = detector(imSmall, 0)
    if len(rects) == 0:
        return 0

    newRect = dlib.rectangle(int(rects[0].left() * FACE_DOWNSAMPLE_RATIO),
                            int(rects[0].top() * FACE_DOWNSAMPLE_RATIO),
                            int(rects[0].right() * FACE_DOWNSAMPLE_RATIO),
                            int(rects[0].bottom() * FACE_DOWNSAMPLE_RATIO))

    points = []
    [points.append((p.x, p.y)) for p in predictor(im, newRect).parts()]
    return points 

# 需要導入模塊: import dlib [as 別名]
# 或者: from dlib import rectangle [as 別名]
def featurize(self, img, bbox):
    """ Compute face feature of the face bounding box in `bbox` in the image `img`.

    :param img: image
    :type img: :class:`numpy.ndarray`
    :param bbox: bounding box dictionary
    :type bbox: dict
    :return: face feature
    :rtype: :class:`numpy.ndarray`
    """
    # Deal with B&W images
    if len(img.shape)==2:
      import skimage
      img = skimage.color.gray2rgb(img)
    # Build dlib rectangle from bounding box
    from dlib import rectangle
    dlib_bbox = rectangle(bbox['left'], bbox['top'], bbox['right'], bbox['bottom'])
    shape = self.sp(img, dlib_bbox)
    # Return feature
    return np.squeeze(self.facerec.compute_face_descriptor(img, shape)) 

# 需要導入模塊: import dlib [as 別名]
# 或者: from dlib import rectangle [as 別名]
def _return_landmarks(self, inputImg, roiX, roiY, roiW, roiH, points_to_return=range(0,68)):
        """ Return the the roll pitch and yaw angles associated with the input image.

        @param image It is a colour image. It must be >= 64 pixel.
        @param radians When True it returns the angle in radians, otherwise in degrees.
        """
        #Creating a dlib rectangle and finding the landmarks
        dlib_rectangle = dlib.rectangle(left=int(roiX), top=int(roiY), right=int(roiW), bottom=int(roiH))
        dlib_landmarks = self._shape_predictor(inputImg, dlib_rectangle)

        #It selects only the landmarks that
        #have been indicated in the input parameter "points_to_return".
        #It can be used in solvePnP() to estimate the 3D pose.
        landmarks = np.zeros((len(points_to_return),2), dtype=np.float32)
        counter = 0
        for point in points_to_return:
            landmarks[counter] = [dlib_landmarks.parts()[point].x, dlib_landmarks.parts()[point].y]
            counter += 1

        return landmarks 

# 需要導入模塊: import dlib [as 別名]
# 或者: from dlib import rectangle [as 別名]
def returnLandmarks(self, inputImg, roiX, roiY, roiW, roiH, points_to_return=range(0,68)):
            #Creating a dlib rectangle and finding the landmarks
            dlib_rectangle = dlib.rectangle(left=int(roiX), top=int(roiY), right=int(roiW), bottom=int(roiH))
            dlib_landmarks = self._predictor(inputImg, dlib_rectangle)

            #It selects only the landmarks that
            # have been indicated in the input parameter "points_to_return".
            #It can be used in solvePnP() to estimate the 3D pose.
            self._landmarks = numpy.zeros((len(points_to_return),2), dtype=numpy.float32)
            counter = 0
            for point in points_to_return:
                self._landmarks[counter] = [dlib_landmarks.parts()[point].x, dlib_landmarks.parts()[point].y]
                counter += 1


            #Estimation of the eye dimesnion
            #self._right_eye_w = self._landmark_matrix[RIGHT_TEAR].item((0,0)) - self._landmark_matrix[RIGHT_EYE].item((0,0)) 
            #self._left_eye_w = self._landmark_matrix[LEFT_EYE].item((0,0)) - self._landmark_matrix[LEFT_TEAR].item((0,0))


            return self._landmarks 

# 需要導入模塊: import dlib [as 別名]
# 或者: from dlib import rectangle [as 別名]
def detect_landmarks(self, frame):
        """Detect 5-point facial landmarks for faces in frame."""
        predictor = get_landmarks_predictor()
        landmarks = []
        for face in frame['faces']:
            l, t, w, h = face
            rectangle = dlib.rectangle(left=int(l), top=int(t), right=int(l+w), bottom=int(t+h))
            landmarks_dlib = predictor(frame['grey'], rectangle)

            def tuple_from_dlib_shape(index):
                p = landmarks_dlib.part(index)
                return (p.x, p.y)

            num_landmarks = landmarks_dlib.num_parts
            landmarks.append(np.array([tuple_from_dlib_shape(i) for i in range(num_landmarks)]))
        frame['landmarks'] = landmarks 

# 需要導入模塊: import dlib [as 別名]
# 或者: from dlib import rectangle [as 別名]
def to_dlib_rect(self):
        import dlib
        return dlib.rectangle(left=self.x1, right=self.x2, top=self.y1, bottom=self.y2) 

# 需要導入模塊: import dlib [as 別名]
# 或者: from dlib import rectangle [as 別名]
def _tuple_to_rect(rect):
    """
    Convert a tuple in (top, right, bottom, left) order to a dlib `rect` object

    :param rect:  plain tuple representation of the rect in (top, right, bottom, left) order
    :return: a dlib `rect` object
    """
    return dlib.rectangle(rect[3], rect[0], rect[1], rect[2]) 

# 需要導入模塊: import dlib [as 別名]
# 或者: from dlib import rectangle [as 別名]
def findLandmarks(self, rgbImg, bb):
        """
        Find the landmarks of a face.
        :param rgbImg: RGB image to process. Shape: (height, width, 3)
        :type rgbImg: numpy.ndarray
        :param bb: Bounding box around the face to find landmarks for.
        :type bb: dlib.rectangle
        :return: Detected landmark locations.
        :rtype: list of (x,y) tuples
        """
        assert rgbImg is not None
        assert bb is not None

        points = self.predictor(rgbImg, bb)
        return list(map(lambda p: (p.x, p.y), points.parts())) 

# 需要導入模塊: import dlib [as 別名]
# 或者: from dlib import rectangle [as 別名]
def __init__(self,bbox,img):
    self.tracker = correlation_tracker()
    self.tracker.start_track(img,rectangle(long(bbox[0]),long(bbox[1]),long(bbox[2]),long(bbox[3])))
    self.confidence = 0. # measures how confident the tracker is! (a.k.a. correlation score)

    self.time_since_update = 0
    self.id = CorrelationTracker.count
    CorrelationTracker.count += 1
    self.hits = 0
    self.hit_streak = 0
    self.age = 0