Adaptive Diagonal Total-Variation Generative Adversarial Network for Super-Resolution Imaging

Abstract

To address problems that the loss function does not correlate well with perceptual vision in super-resolution methods based on the convolutional neural network(CNN), a novel model called the ADTV-SRGAN is designed based on the adaptive diagonal total-variation generative adversarial network. Combined with global perception and the local structure adaptive method, spatial loss based on the diagonal variation model is proposed to make the loss function can be adjusted according to the spatial features. Pixel loss and characteristic loss are in combination with the spatial loss for the fusing optimization of the total loss function such that high-frequency details of the images are maintained to improve their quality. The results of experiment show that the proposed method can obtain competitive results in objective evaluations. In subjective assessment, images reconstructed by it are clear, delicate, and natural, and it preserved edgeand texture-related details.

Color Image Retrieval Algorithm Fusing Color and Principal Curvatures Information

“…At the same time, the sampling mode (8,32) has the best performance in all modes, whose mAP is 84.05% in space1 and 83.83% in space2. If sampling radius is smaller, the extracted features will be more complete, but it will cost more time, such as (4,8). In addition, the mAP is related to the vector length, so the vector length of specified sampling mode will be further analyzed in next section.…”

“…With the application of computer vision and digital devices, image processing is more and more widely used in medical images [1], [2], image super-resolution [3], [4], remote sensing images [5], and other fields such as social applications [6], [7]. Nowadays, benefiting from the rapid development of image processing, people can get access to image resources quickly.…”