Shear

If you have ever worked on a Computer Vision project, you might know that using augmentations to diversify the dataset is the best practice. On this page, we will:

• Сover the Shear augmentation;

• Check out its parameters;

• See how Shear affects an image;

• And check out how to work with Shear using Python through the Albumentations library.

Let’s jump in.

Shear explained

To define the term, Shear is a geometric augmentation that changes a form of an image along a specific axis to create a different perception angle.

As you can see in the picture above, Shear moves a side of an image, transforming its initial form of a square into a trapezoid. Shears are applied sequentially if you want to shear your image along the x- and y-axis. Data Scientists use Shear to augment pictures in such a way that an algorithm can identify an object from multiple angles.

Parameters

• Shear in degrees - specifies the range of degrees that is used to sample x- and y-shear angle values;
• Probability of applying transform - defines the likelihood of applying Shear to an image.

Shear visualized

Code implementation

    import albumentations as albu
from PIL import Image
import numpy as np


transform = albu.augmentations.geometric.transforms.Affine(shear = {'x': -45, 'y': 45})
image = np.array(Image.open('/some/random/image.png'))
augmented_image = transform(image=image)['image']

# We have the transformed image in augmented_image.
    Copy
  

Learn more about other augmentations …

• Horizontal Flip;
• Vertical Flip;
• Random Crop;
• Random Sized Crop;
• Rotate;
• Resize;
• Blur;
• Smallest max size;
• Center Crop;
• Color Jitter;
• Shift Scale Rotate;
• Longest Max Size;
• Equalize;
• To gray;
• Mosaic;
• Copy Paste.