AutoContrast

Targets:

image

Image Types:uint8, float32

Stretch intensity to full range (autocontrast). method: CDF or PIL-style. cutoff, ignore trim extremes. Use for normalizing brightness/contrast across images.

This transform provides two methods for contrast enhancement:

CDF method (default): Uses cumulative distribution function for more gradual adjustment
PIL method: Uses linear scaling like PIL.ImageOps.autocontrast

The transform can optionally exclude extreme values from both ends of the intensity range and preserve specific intensity values (e.g., alpha channel).

Arguments

cutoff

float

Percentage of pixels to exclude from both ends of the histogram. Range: [0, 100]. Default: 0 (use full intensity range)

0 means use the minimum and maximum intensity values found
20 means exclude darkest and brightest 20% of pixels

ignore

int | None

Intensity value to preserve (e.g., alpha channel). Range: [0, 255]. Default: None

If specified, this intensity value will not be modified
Useful for images with alpha channel or special marker values

method

cdf | pil

cdf

Algorithm to use for contrast enhancement. Default: "cdf"

"cdf": Uses cumulative distribution for smoother adjustment
"pil": Uses linear scaling like PIL.ImageOps.autocontrast

p

float

0.5

Probability of applying the transform. Default: 0.5

Examples

>>> import albumentations as A
>>> # Basic usage
>>> transform = A.AutoContrast(p=1.0)
>>>
>>> # Exclude extreme values
>>> transform = A.AutoContrast(cutoff=20, p=1.0)
>>>
>>> # Preserve alpha channel
>>> transform = A.AutoContrast(ignore=255, p=1.0)
>>>
>>> # Use PIL-like contrast enhancement
>>> transform = A.AutoContrast(method="pil", p=1.0)

Notes

The transform processes each color channel independently
For grayscale images, only one channel is processed
The output maintains the same dtype as input
Empty or single-color channels remain unchanged