Deep learning enables a model constituted by multiple processing layers to learn the data representation with multiple levels of abstraction. In the past decade, deep learning has brought remarkable achievements in many fields of machine learning and pattern recognition, especially in image processing. The state-of-the-art performance in image super-resolution reconstruction, image classification, target detection, image retrieval and other image processing tasks have been greatly improved. This book introduces these image processing technologies based on deep learning, including recent advances, applications in real scenes and future trends. The first chapter introduces image super-resolution reconstruction, which aims to recover high-resolution images from corresponding low-resolution versions. This chapter reviews these image super-resolution methods based on convolutional neural networks and generative adversarial networks on account of internal network structure. The second chapter presents four categories of few-shot image classification algorithms: transfer learning based, meta-learning based, data augmentation based, and multimodal based methods. In the third chapter, deep learning based models for small target detection in video are summarized in detail, which are categorized into one-stage models and two-stage models according to the detection stages. The network structures and plug-in modules for video based small target detection are also explained. The fourth chapter discusses deep learning based cross-modal hashing for image retrieval methods, including the extraction of high-level semantic information and the maintenance of similarity between different mo