Summary of 12 commonly used image data enhancement techniques

The goal of training a machine learning or deep learning model is to become a "universal" model. This requires that the model does not overfit the training data set, or in other words, our model has a good understanding of the unseen data. Data augmentation is also one of many ways to avoid overfitting.

The process of expanding the amount of data used to train a model is called data augmentation. By training a model with multiple data types, we can obtain a more "generalized" model. What does "multiple data types" mean? This article only discusses "image" data enhancement technology and only introduces various image data enhancement strategies in detail. We will also get hands-on and implement data augmentation techniques primarily used in image data or computer vision using PyTorch.

Because it introduces data enhancement technology. So just use one image. Let’s look at the visual code first.

import PIL.Image as Image
 import torch
 from torchvision import transforms
 import matplotlib.pyplot as plt
 import numpy as np
 import warnings
 
 def imshow(img_path, transform):

Resize/Rescale

This function is used to adjust the height and width of the image to what we want. specific size. The code below demonstrates that we want to resize the image from its original size to 224 x 224.

path = './kitten.jpeg'
 transform = transforms.Resize((224, 224))
 imshow(path, transform)

Cropping

This technique applies a portion of a selected image to a new image. For example, use CenterCrop to return a center-cropped image.

transform = transforms.CenterCrop((224, 224))
 imshow(path, transform)

RandomResizedCrop

This method combines cropping and resizing at the same time.

transform = transforms.RandomResizedCrop((100, 300))
 imshow(path, transform)

Flipping

Flip the image horizontally or vertically, the code below will try to apply a horizontal flip to our image.

transform = transforms.RandomHorizontalFlip()
 imshow(path, transform)

Padding

Padding consists of padding a specified amount on all edges of the image. We'll fill each edge with 50 pixels.

transform = transforms.Pad((50,50,50,50))
 imshow(path, transform)

Rotation

Applies a random rotation angle to the image. We'll set this angle to 15 degrees.

transform = transforms.RandomRotation(15)
 imshow(path, transform)

Random Affine

This technique is a transformation that leaves the center unchanged. This technique has some parameters:

• degrees: rotation angle
• translate: horizontal and vertical translation
• scale: scaling parameters
• share: Image cropping parameters
• fillcolor: The color of the outer fill of the image

transform = transforms.RandomAffine(1, translate=(0.5, 0.5), scale=(1, 1), shear=(1,1), fillcolor=(256,256,256))
 imshow(path, transform)

Gaussian Blur

The image will be blurred using Gaussian blur deal with.

transform = transforms.GaussianBlur(7, 3)
 imshow(path, transform)

Grayscale

Convert color images to grayscale.

transform = transforms.Grayscale(num_output_channels=3)
 imshow(path, transform)

Color enhancement, also known as color dithering, is the process of modifying the color properties of an image by changing its pixel values. The following methods are all color-related operations.

Brightness

Change the brightness of the image The resulting image becomes darker or lighter when compared to the original image.

transform = transforms.ColorJitter(brightness=2)
 imshow(path, transform)

Contrast

The degree of difference between the darkest and lightest parts of an image is called contrast. The contrast of the image can also be adjusted as an enhancement.

transform = transforms.ColorJitter(cnotallow=2)
 imshow(path, transform)

Saturation

Summary of 12 commonly used image data enhancement techniques中颜色的分离被定义为饱和度。

transform = transforms.ColorJitter(saturatinotallow=20)
 imshow(path, transform)

Hue

色调被定义为Summary of 12 commonly used image data enhancement techniques中颜色的深浅。

transform = transforms.ColorJitter(hue=2)
 imshow(path, transform)

总结

图像本身的变化将有助于模型对未见数据的泛化，从而不会对数据进行过拟合。以上整理的都是我们常见的数据增强技术，torchvision中还包含了很多方法，可以在他的文档中找到：https://pytorch.org/vision/stable/transforms.html

The above is the detailed content of Summary of 12 commonly used image data enhancement techniques. For more information, please follow other related articles on the PHP Chinese website!