mindspore.dataset.vision.Perspective

class mindspore.dataset.vision.Perspective(start_points, end_points, interpolation=Inter.BILINEAR)[source]

Apply perspective transformation on input image.

Parameters

start_points (Sequence[Sequence[int, int]]) – Sequence of the starting point coordinates, containing four two-element subsequences, corresponding to [top-left, top-right, bottom-right, bottom-left] of the quadrilateral in the original image.
end_points (Sequence[Sequence[int, int]]) – Sequence of the ending point coordinates, containing four two-element subsequences, corresponding to [top-left, top-right, bottom-right, bottom-left] of the quadrilateral in the target image.
interpolation (Inter, optional) –
Method of interpolation. It can be Inter.BILINEAR, Inter.LINEAR, Inter.NEAREST, Inter.AREA, Inter.PILCUBIC, Inter.CUBIC or Inter.BICUBIC. Default: Inter.BILINEAR.
- Inter.BILINEAR, bilinear interpolation.
- Inter.LINEAR, linear interpolation, the same as Inter.BILINEAR.
- Inter.NEAREST, nearest-neighbor interpolation.
- Inter.BICUBIC, bicubic interpolation.
- Inter.CUBIC, cubic interpolation, the same as Inter.BICUBIC.
- Inter.PILCUBIC, cubic interpolation based on the implementation of Pillow, only numpy.ndarray input is supported.
- Inter.AREA, pixel area interpolation, only numpy.ndarray input is supported.

Raises

TypeError – If start_points is not of type Sequence[Sequence[int, int]].
TypeError – If end_points is not of type Sequence[Sequence[int, int]].
TypeError – If interpolation is not of type mindspore.dataset.vision.Inter .
RuntimeError – If shape of the input image is not <H, W> or <H, W, C>.

Supported Platforms:: CPU

Examples

>>> from mindspore.dataset.transforms import Compose
>>> from mindspore.dataset.vision import Inter
>>>
>>> start_points = [[0, 63], [63, 63], [63, 0], [0, 0]]
>>> end_points = [[0, 32], [32, 32], [32, 0], [0, 0]]
>>> transforms_list = Compose([vision.Decode(),
...                            vision.Perspective(start_points, end_points, Inter.BILINEAR)])
>>> # apply the transform to dataset through map function
>>> image_folder_dataset = image_folder_dataset.map(operations=transforms_list,
...                                                 input_columns="image")