ISONoise

Targets:

image

Image Types:uint8, float32

Add camera-sensor-like noise scaling with intensity (high ISO). color_shift and intensity range control strength. Good for low-light or camera noise simulation.

This transform adds random noise to an image, mimicking the effect of using high ISO settings in digital photography. It simulates two main components of ISO noise:

Color noise: random shifts in color hue
Luminance noise: random variations in pixel intensity

Arguments

color_shift

tuple[float, float]

[0.01,0.05]

Range for changing color hue. Values should be in the range [0, 1], where 1 represents a full 360° hue rotation. Default: (0.01, 0.05)

intensity

tuple[float, float]

[0.1,0.5]

Range for the noise intensity. Higher values increase the strength of both color and luminance noise. Default: (0.1, 0.5)

p

float

0.5

Probability of applying the transform. Default: 0.5

Examples

>>> import numpy as np
>>> import albumentations as A
>>> image = np.random.randint(0, 256, (100, 100, 3), dtype=np.uint8)
>>> transform = A.ISONoise(color_shift=(0.01, 0.05), intensity=(0.1, 0.5), p=0.5)
>>> result = transform(image=image)
>>> noisy_image = result["image"]

Notes

This transform only works with RGB images. It will raise a TypeError if applied to non-RGB images.
The color shift is applied in the HSV color space, affecting the hue channel.
Luminance noise is added to all channels independently.
This transform can be useful for data augmentation in low-light scenarios or when training models to be robust against noisy inputs.

References

ISO noise in digital photographyhttps://en.wikipedia.org/wiki/Image_noise#In_digital_cameras