A Comprehensive Survey on Deep Learning-Based Image Processing

Abstract

Over the past decade, deep learning has made rapid advancements, achieving significant breakthroughs in the field of image processing. This survey aims to provide a comprehensive overview of recent developments in deep learning-based image processing technologies. It begins by introducing the foundational principles of deep learning and commonly employed network architectures, such as Convolutional Neural Networks (CNNs), Generative Adversarial Networks (GANs), and the ELM-RVFL series. These architectures have found widespread applicability in various image-processing tasks. The survey then delves into the current state of deep learning in key areas such as image classification, object detection, and image segmentation, where deep learning models have consistently outperformed traditional methods in terms of both accuracy and efficiency. Moreover, it examines diverse applications of deep learning in fields including face recognition, medical imaging, and pedestrian detection, which have led to notable improvements in accuracy, robustness, and overall performance. Finally, the survey highlights the symbiotic relationship between deep learning and image processing, exploring potential future directions for novel deep learning models and advanced training methodologies. These insights aim to inspire further research into innovative approaches to deep learning in image processing, ultimately contributing to the continued advancement of image processing technologies and their broad range of applications.