ElasticTransform

Targets:

image

mask

bboxes

keypoints

Image Types:uint8, float32

Apply elastic deformation to images, masks, bboxes, keypoints. Params: alpha, sigma, interpolation. Uses Gaussian-smoothed random displacement fields.

This transformation introduces random elastic distortions to the input data. It's particularly useful for data augmentation in training deep learning models, especially for tasks like image segmentation or object detection where you want to maintain the relative positions of features while introducing realistic deformations.

The transform works by generating random displacement fields and applying them to the input. These fields are smoothed using a Gaussian filter to create more natural-looking distortions.

Targets: image, mask, bboxes, keypoints, volume, mask3d

Image types: uint8, float32

Supported bboxes: hbb, obb

Arguments

alpha

float

Scaling factor for the random displacement fields. Higher values result in more pronounced distortions. Default: 1.0

sigma

float

Standard deviation of the Gaussian filter used to smooth the displacement fields. Higher values result in smoother, more global distortions. Default: 50.0

interpolation

0 | 1 | 2 | 3 | 4

Interpolation method to be used for image transformation. Should be one of the OpenCV interpolation types. Default: cv2.INTER_LINEAR

approximate

bool

false

Whether to use an approximate version of the elastic transform. If True, uses a fixed kernel size for Gaussian smoothing, which can be faster but potentially less accurate for large sigma values. Default: False

same_dxdy

bool

false

Whether to use the same random displacement field for both x and y directions. Can speed up the transform at the cost of less diverse distortions. Default: False

mask_interpolation

0 | 1 | 2 | 3 | 4

Flag that is used to specify the interpolation algorithm for mask. Should be one of: cv2.INTER_NEAREST, cv2.INTER_LINEAR, cv2.INTER_CUBIC, cv2.INTER_AREA, cv2.INTER_LANCZOS4. Default: cv2.INTER_NEAREST.

noise_distribution

gaussian | uniform

gaussian

Distribution used to generate the displacement fields. "gaussian" generates fields using normal distribution (more natural deformations). "uniform" generates fields using uniform distribution (more mechanical deformations). Default: "gaussian".

keypoint_remapping_method

direct | mask

mask

Method to use for keypoint remapping.

"mask": Uses mask-based remapping. Faster, especially for many keypoints, but may be less accurate for large distortions. Recommended for large images or many keypoints.
"direct": Uses inverse mapping. More accurate for large distortions but slower. Default: "mask"

p

float

0.5

Probability of applying the transform. Default: 0.5

Examples

>>> import albumentations as A
>>> transform = A.Compose([
...     A.ElasticTransform(alpha=1, sigma=50, p=0.5),
... ])
>>> transformed = transform(image=image, mask=mask, bboxes=bboxes, keypoints=keypoints)
>>> transformed_image = transformed['image']
>>> transformed_mask = transformed['mask']
>>> transformed_bboxes = transformed['bboxes']
>>> transformed_keypoints = transformed['keypoints']

Notes

The transform will maintain consistency across all targets (image, mask, bboxes, keypoints) by using the same displacement fields for all.
The 'approximate' parameter determines whether to use a precise or approximate method for generating displacement fields. The approximate method can be faster but may be less accurate for large sigma values.
Bounding boxes that end up outside the image after transformation will be removed.
Keypoints that end up outside the image after transformation will be removed.

>>> import albumentations as A >>> transform = A.Compose([ ... A.ElasticTransform(alpha=1, sigma=50, p=0.5), ... ]) >>> transformed = transform(image=image, mask=mask, bboxes=bboxes, keypoints=keypoints) >>> transformed_image = transformed['image'] >>> transformed_mask = transformed['mask'] >>> transformed_bboxes = transformed['bboxes'] >>> transformed_keypoints = transformed['keypoints']