Abstract
During the past decade, deep learning is one of the essential breakthroughs made in artificial intelligence. In particular, it has achieved great success in image processing. Correspondingly, various applications related to image processing are also promoting the rapid development of deep learning in all aspects of network structure, layer designing, and training tricks. However, the deeper structure makes the back-propagation algorithm more difficult. At the same time, the scale of training images without labels is also rapidly increasing, and class imbalance severely affects the performance of deep learning, these urgently require more novelty deep models and new parallel computing system to more effectively interpret the content of the image and form a suitable analysis mechanism. In this context, this survey provides four deep learning model series, which includes CNN series, GAN series, ELM-RVFL series, and other series, for comprehensive understanding towards the analytical techniques of image processing field, clarify the most important advancements and shed some light on future studies. By further studying the relationship between deep learning and image processing tasks, which can not only help us understand the reasons for the success of deep learning but also inspires new deep models and training methods. More importantly, this survey aims to improve or arouse other researchers to catch a glimpse of the state-of-the-art deep learning methods in the field of image processing and facilitate the applications of these deep learning technologies in their research tasks. Besides, we discuss the open issues and the promising directions of future research in image processing using the new generation of deep learning.
Highlights
Since images play an essential role in our daily life, and as the advances in computer information collection systems, one can obtain more and more image sets, but most of them cannot be processed manually [1]–[3]
We mainly introduce several new generations of deep learning techniques that have used for image processing, and that referred to throughout the survey
OPEN ISSUES AND COPING STRATEGIES In practice, the lack of large training datasets with labels has been repeatedly mentioned for various image processing application tasks
Summary
Since images play an essential role in our daily life, and as the advances in computer information collection systems, one can obtain more and more image sets, but most of them cannot be processed manually [1]–[3]. According to the different requirements of the application task, at the same time, to solve the existing problems of classical deep learning (such as AE, CNN, DBN, RNN, and GAN, etc.), a variety of new generation algorithms and frameworks of deep learning have proposed. We analysis the fundamental theoretical insights about the new generation deep networks in detail, it seems the pressing need for deep learning nowadays This survey aims to improve or arouse other researchers to catch a glimpse of the state-of-the-art deep learning methods in the field of image processing and facilitate the applications of these deep learning technologies in their research tasks. It is worth pointing out that, as far as many neurocognitive mechanisms are still further developed and perfected, the work of network modeling based on biological neural enlightenment is still a long way off The rest of this survey as structured as followed.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
