FancyPCA

Targets:

image

Image Types:uint8, float32

Add color variation via PCA on RGB: perturb components by alpha_std. Simulates natural lighting variation (ImageNet-style). Good for object recognition.

This augmentation technique applies PCA (Principal Component Analysis) to the image's color channels, then adds multiples of the principal components to the image, with magnitudes proportional to the corresponding eigenvalues times a random variable drawn from a Gaussian with mean 0 and standard deviation 'alpha'.

Arguments

alpha

float

0.1

Standard deviation of the Gaussian distribution used to generate random noise for each principal component. Default: 0.1.

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.FancyPCA(alpha=0.1, p=1.0)
>>> result = transform(image=image)
>>> augmented_image = result["image"]

Notes

This augmentation is particularly effective for RGB images but can work with any number of channels.
For grayscale images, it applies a simplified version of the augmentation.
The transform preserves the mean of the image while adjusting the color/intensity variation.
This implementation is based on the paper by Krizhevsky et al. and is similar to the one used in the original AlexNet paper.

References

ImageNet Classification with Deep Convolutional Neural NetworksIn Advances in Neural Information