Class MaskToBox

monai/apps/detection/transforms/array.py:437–472

Convert int16 mask image to box, which has the same size with the input image. Pairs with :py:class:`monai.apps.detection.transforms.array.BoxToMask`. Please make sure the same ``min_fg_label`` is used when using the two transforms in pairs. Args: bg_label: background label

class MaskToBox(Transform):
    """
    Convert int16 mask image to box, which has the same size with the input image.
    Pairs with :py:class:`monai.apps.detection.transforms.array.BoxToMask`.
    Please make sure the same ``min_fg_label`` is used when using the two transforms in pairs.

    Args:
        bg_label: background labels for the output mask image, make sure it is smaller than any foreground(fg) labels.
        box_dtype: output dtype for boxes
        label_dtype: output dtype for labels
    """

    backend = [TransformBackends.NUMPY]

    def __init__(
        self,
        bg_label: int = -1,
        box_dtype: DtypeLike | torch.dtype = torch.float32,
        label_dtype: DtypeLike | torch.dtype = torch.long,
    ) -> None:
        self.bg_label = bg_label
        self.box_dtype = box_dtype
        self.label_dtype = label_dtype

    def __call__(self, boxes_mask: NdarrayOrTensor) -> tuple[NdarrayOrTensor, NdarrayOrTensor]:
        """
        Args:
            boxes_mask: int16 array, sized (num_box, H, W). Each channel represents a box.
                The foreground region in channel c has intensity of labels[c].
                The background intensity is bg_label.

        Return:
            - bounding boxes, Nx4 or Nx6 torch tensor or ndarray. The box mode is assumed to be ``StandardMode``.
            - classification foreground(fg) labels, dtype should be int, sized (N,).
        """
        return convert_mask_to_box(boxes_mask, self.bg_label, self.box_dtype, self.label_dtype)


class SpatialCropBox(SpatialCrop):