Research on image Inpainting algorithm of improved GAN based on two-discriminations networks
- PDF / 2,137,699 Bytes
- 15 Pages / 595.276 x 790.866 pts Page_size
- 56 Downloads / 172 Views
Research on image Inpainting algorithm of improved GAN based on two-discriminations networks Yuantao Chen 1 & Haopeng Zhang 1 & Linwu Liu 1 & Xi Chen 1 & Qian Zhang 2 & Kai Yang 2 & Runlong Xia 3 & Jingbo Xie 3 Accepted: 23 September 2020 # Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract All existing image inpainting methods based on neural network models are affected by structural distortions and blurred textures on visible connectivity, such that overfitting and overlearning phenomena can easily emerge in the image inpainting processing procedure. Accordingly, in an attempt to address the defects of image inpainting algorithm, such as long iteration time, poor adaptability and unsatisfactory repairing effects, the image inpainting algorithm of improved Generative Adversarial Networks based on deep learning method of Two-Discriminations Network has been proposed in the paper. The proposed method uses image inpainting network, global discrimination network and local discrimination network to create a fusion network to apply computational images. In the training procedure of proposed algorithm, the network of image inpainting algorithm uses similar patching method to fill the broken area in image and set it as input training objects, which greatly improves the speed and quality of image inpainting. The global discrimination network uses global structure with marginal information and feature information to judge the completed image, meaning that it comprehensively achieves visible connectivity. As local discrimination network can judge the computational images, it has also been trained with assisted feature patches found on multiple images. Furthermore, the proposed method can enhance the discriminant capability and solve the problem that the image inpainting network has easily been overfitting when the features are too concentrated and limited in number to process. Our results of designed experiments demonstrate that proposed algorithm has better adaptive capability on several image categories than those state-of-the-arts. Keywords Generative adversarial networks . Global discrimination network . Local discrimination network . Adaptive capability . Image Inpainting
1 Introduction The image inpainting operation is the practical use of the computer to fill and repair broken areas of source image in order to finally achieve visualization rationality. Moreover, an image inpainting algorithm is a kind of image processing method that repairs missing information in an original image, or removes specific information in an image by using * Yuantao Chen [email protected] 1
School of Computer and Communication Engineering & Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation, Changsha University of Science and Technology, Changsha 410114, Hunan, China
2
Department of Electronic Products, Hunan ZOOMLION Intelligent Technology Corporation Limited, Changsha 410005, Hunan, China
3
Hunan Institute of Scientific and Technical Information, Changsha 411105, Hunan
Data Loading...
