tf.keras.ops.image.perspective_transform

Applies a perspective transformation to the image(s).

tf.keras.ops.image.perspective_transform(
    images,
    start_points,
    end_points,
    interpolation='bilinear',
    fill_value=0,
    data_format=None
)

images Input image or batch of images. Must be 3D or 4D.
start_points A tensor of shape (N, 4, 2) or (4, 2), representing the source points in the original image that define the transformation.
end_points A tensor of shape (N, 4, 2) or (4, 2), representing the target points in the output image after transformation.
interpolation Interpolation method. Available methods are "nearest", and "bilinear". Defaults to "bilinear".
fill_value Value used for points outside the boundaries of the input if extrapolation is needed. Defaults to 0.
data_format A string specifying the data format of the input tensor. It can be either "channels_last" or "channels_first". "channels_last" corresponds to inputs with shape (batch, height, width, channels), while "channels_first" corresponds to inputs with shape (batch, channels, height, width). If not specified, the value will default to keras.config.image_data_format.

Applied perspective transform image or batch of images.

Examples:

x = np.random.random((2, 64, 80, 3))  # batch of 2 RGB images
start_points = np.array(
    [
        [[0, 0], [0, 64], [80, 0], [80, 64]],
        [[0, 0], [0, 64], [80, 0], [80, 64]],
    ]
)
end_points = np.array(
    [
        [[3, 5], [7, 64], [76, -10], [84, 61]],
        [[8, 10], [10, 61], [65, 3], [88, 43]],
    ]
)
y = keras.ops.image.perspective_transform(x, start_points, end_points)
y.shape
(2, 64, 80, 3)
 
x = np.random.random((64, 80, 3))  # single RGB image
start_points = np.array([[0, 0], [0, 64], [80, 0], [80, 64]])
end_points = np.array([[3, 5], [7, 64], [76, -10], [84, 61]])
y = keras.ops.image.perspective_transform(x, start_points, end_points)
y.shape
(64, 80, 3)
 
x = np.random.random((2, 3, 64, 80))  # batch of 2 RGB images
start_points = np.array(
    [
        [[0, 0], [0, 64], [80, 0], [80, 64]],
        [[0, 0], [0, 64], [80, 0], [80, 64]],
    ]
)
end_points = np.array(
    [
        [[3, 5], [7, 64], [76, -10], [84, 61]],
        [[8, 10], [10, 61], [65, 3], [88, 43]],
    ]
)
y = keras.ops.image.perspective_transform(
    x, start_points, end_points, data_format="channels_first"
)
y.shape
(2, 3, 64, 80)