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 Center Crop augmentation;
  • Check out its parameters;
  • See how Center Crop affects an image;
  • And check out how to work with Center Crop using Python through the Albumentations library.

Let’s jump in.

To define the term, Center Crop is a data augmentation technique that helps researchers to crop images to a specified height and width with a certain probability.

The key difference between Random Crop and Center Crop is that the latter crops the central part of an image.
  • Height - defines the height of the newly cropped image in pixels;
  • Width - defines the width of the newly cropped image in pixels;
  • Probability - the probability that the transformation will be applied to an image.
Original image
Image after Center Crop was applied (height = 128, width = 300, probability = 1)
python
      import albumentations as albu
from PIL import Image
import numpy as np

transform =albu.CenterCrop(200,200,p=0.5)#set height, width, and probability

image = np.array(Image.open('/some/image/file/path'))
image = transform(image=image)['image']

# Now the image is cropped and ready to be accepted by the model
    

Accelerated Annotation.
Maximize model performance quickly with AI-powered labeling and 100% QA.

Learn more
Last modified