Book Image

Data Augmentation with Python

By : Duc Haba
Book Image

Data Augmentation with Python

By: Duc Haba

Overview of this book

Data is paramount in AI projects, especially for deep learning and generative AI, as forecasting accuracy relies on input datasets being robust. Acquiring additional data through traditional methods can be challenging, expensive, and impractical, and data augmentation offers an economical option to extend the dataset. The book teaches you over 20 geometric, photometric, and random erasing augmentation methods using seven real-world datasets for image classification and segmentation. You’ll also review eight image augmentation open source libraries, write object-oriented programming (OOP) wrapper functions in Python Notebooks, view color image augmentation effects, analyze safe levels and biases, as well as explore fun facts and take on fun challenges. As you advance, you’ll discover over 20 character and word techniques for text augmentation using two real-world datasets and excerpts from four classic books. The chapter on advanced text augmentation uses machine learning to extend the text dataset, such as Transformer, Word2vec, BERT, GPT-2, and others. While chapters on audio and tabular data have real-world data, open source libraries, amazing custom plots, and Python Notebook, along with fun facts and challenges. By the end of this book, you will be proficient in image, text, audio, and tabular data augmentation techniques.
Table of Contents (17 chapters)
Part 1: Data Augmentation
Part 2: Image Augmentation
Part 3: Text Augmentation
Part 4: Audio Data Augmentation
Part 5: Tabular Data Augmentation

Photometric transformations

Photometric transformations are also known as lighting transformations.

An image is represented in a three-dimensional array or a rank 3 tensor, and the first two dimensions are the picture’s width and height coordinates for each pixel position. The third dimension is a red, blue, and green (RGB) value ranging from zero to 255 or #0 to #FF in hexadecimal. The equivalent of RGB in printing is cyan, magenta, yellow, and key (CMYK). The other popular format is hue, saturation, and value (HSV). The salient point is that a photo is a matrix of an integer or float when normalized.

Visualizing the image as a matrix of numbers makes it easy to transform it. For example, in HSV format, changing the saturation value to zero in the matrix will convert an image from color into grayscale.

Dozens of filters alter the color space characteristics, from the basics to exotic ones. The basic methods are darkened, lightened, sharpened, blurring, contrast, and...