ToSepia

Targets:

image

volume

Image Types:uint8, float32

Apply a sepia filter to the input image.

This transform converts a color image to a sepia tone, giving it a warm, brownish tint that is reminiscent of old photographs. The sepia effect is achieved by applying a specific color transformation matrix to the RGB channels of the input image. For grayscale images, the transform is a no-op and returns the original image.

Arguments

p

float

0.5

Probability of applying the transform. Default: 0.5.

Examples

>>> import numpy as np
>>> import albumentations as A
>>>
# Apply sepia effect to a uint8 RGB image
>>> image = np.random.randint(0, 256, (100, 100, 3), dtype=np.uint8)
>>> transform = A.ToSepia(p=1.0)
>>> sepia_image = transform(image=image)['image']
>>> assert sepia_image.shape == image.shape
>>> assert sepia_image.dtype == np.uint8
>>>
# Apply sepia effect to a float32 RGB image
>>> image = np.random.rand(100, 100, 3).astype(np.float32)
>>> transform = A.ToSepia(p=1.0)
>>> sepia_image = transform(image=image)['image']
>>> assert sepia_image.shape == image.shape
>>> assert sepia_image.dtype == np.float32
>>> assert 0 <= sepia_image.min() <= sepia_image.max() <= 1.0
>>>
# No effect on grayscale images
>>> gray_image = np.random.randint(0, 256, (100, 100), dtype=np.uint8)
>>> transform = A.ToSepia(p=1.0)
>>> result = transform(image=gray_image)['image']
>>> assert np.array_equal(result, gray_image)

Notes

The sepia effect only works with RGB images (3 channels). For grayscale images, the original image is returned unchanged since the sepia transformation would have no visible effect when R=G=B.
The sepia effect is created using a fixed color transformation matrix: [[0.393, 0.769, 0.189], [0.349, 0.686, 0.168], [0.272, 0.534, 0.131]]
The output image will have the same data type as the input image.
For float32 images, ensure the input values are in the range [0, 1].