This survey focuses on Data Augmentation, a technique to enhance training datasets and improve the performance of Deep Learning models, particularly in scenarios with limited data. The survey covers various image augmentation algorithms, including geometric transformations, color space augmentations, kernel filters, mixing images, random erasing, feature space augmentation, adversarial training, generative adversarial networks (GANs), neural style transfer, and meta-learning. It also discusses the application of GANs in data augmentation and other characteristics such as test-time augmentation, resolution impact, final dataset size, and curriculum learning. The survey aims to provide readers with a comprehensive understanding of how Data Augmentation can improve model performance and expand limited datasets to leverage big data capabilities. The introduction highlights the challenges of overfitting and the importance of generalization in Deep Learning models, while the background section provides historical context and key developments in Data Augmentation and Deep Learning. The image data augmentation techniques section delves into the details of each augmentation method, experimental results, and potential disadvantages. The survey concludes with a discussion on the presented material, future work, and conclusions.This survey focuses on Data Augmentation, a technique to enhance training datasets and improve the performance of Deep Learning models, particularly in scenarios with limited data. The survey covers various image augmentation algorithms, including geometric transformations, color space augmentations, kernel filters, mixing images, random erasing, feature space augmentation, adversarial training, generative adversarial networks (GANs), neural style transfer, and meta-learning. It also discusses the application of GANs in data augmentation and other characteristics such as test-time augmentation, resolution impact, final dataset size, and curriculum learning. The survey aims to provide readers with a comprehensive understanding of how Data Augmentation can improve model performance and expand limited datasets to leverage big data capabilities. The introduction highlights the challenges of overfitting and the importance of generalization in Deep Learning models, while the background section provides historical context and key developments in Data Augmentation and Deep Learning. The image data augmentation techniques section delves into the details of each augmentation method, experimental results, and potential disadvantages. The survey concludes with a discussion on the presented material, future work, and conclusions.