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

Character augmenting

Character augmentation substitutes or injects characters into the text. In other words, it creates typing errors. Therefore, the method seems counterintuitive. Still, just like noise injection in image augmentation, scholarly published papers illustrate the benefit of character augmentation in improving AI forecasting accuracy, such as Effective Character-Augmented Word Embedding for Machine Reading Comprehension by Zhuosheng Zhang, Yafang Huang, Pengfei Zhu, and Hai Zhao, from the 2018 CCF International Conference on Natural Language Processing.

The three standard methods for character augmentation are listed as follows:

  • The Optical Character Recognition (OCR) augmenting function substitutes frequent errors in OCR by converting images into text, such as the letter o into the number 0 or the capital letter I into the number 1.
  • The Keyboard augmenting method replaces a character with other characters that are adjacent to it. For example, a typical...