Improving image quality is an important subject in the field of image processing. Images have a wide range of important uses in modern society, such as security surveillance, remote conferences, medical images, etc. Different from drawing-based graphics, it is often difficult to obtain images with sufficient accuracy due to the accuracy of the acquisition equipment. Especially in the field of video surveillance, because of the large amount of data storage, the limited bandwidth of the transmission link, and the limitations of the CCD manufacturing process and cost, it is often difficult to improve the resolution of the camera. The purpose of this paper is to study image resolution enhancement techniques based on deep neural networks. In this paper, in order to solve the problem of image resolution enhancement, the related theories and methods of super-resolution are studied. A processing framework for resolution enhancement is designed for real images. The effect of the resolution enhancement method is improved through process. Normalization method. Aiming at image resolution enhancement, a resolution enhancement method based on deep neural networks is proposed. Through the enhancement of various images, the visual effect of the experimental results is effectively improved. The research results show that image resolution enhancement processing can improve the spatial resolution of images under the same hardware conditions to a certain extent, improve image degradation and resolution degradation due to insufficient hardware conditions, and make up for the lack of image resolution to a certain extent to make the image clearer.
Deep neural network Image resolution Resolution enhancement technology Image application
This is a preview of subscription content, log in to check access.
Park, J., Kim, J., Lee, D.: Application of multi-frame based super-resolution algorithm for a color recognition enhancement for the UAV. J. Korean Soc. Aeronaut. Space Sci. 45(3), 180–190 (2017)Google Scholar
Gharbi, M., Chen, J., Barron, J.T.: Deep bilateral learning for real-time image enhancement. ACM Trans. Graph. 36(4), 118 (2017)CrossRefGoogle Scholar
Li, B., Bin, H., Yang, Y.: Demagnification imaging improved by mask in a hyperlens photolithography system. Plasmonics 12(3), 735–741 (2017)CrossRefGoogle Scholar
Kwon, K.-C., Kwon, K.H., Erdenebat, M.-U.: Resolution-enhancement for an integral imaging microscopy using deep learning. IEEE Photonics J. 11(1), 1–12 (2019)CrossRefGoogle Scholar
Zeng, T., Zhang, T., Tian, W.: Space-surface bistatic SAR image enhancement based on repeat-pass coherent fusion with Beidou-2/Compass-2 as illuminators. IEEE Geosci. Remote Sens. Lett. 13(12), 1832–1836 (2017)CrossRefGoogle Scholar
Thibon, L., Lorenzo, L.E., Piché, M.: Resolution enhancement in confocal microscopy using Bessel-Gauss beams. Opt. Express 25(3), 2162 (2017)CrossRefGoogle Scholar
Jiang, Z., Pan, X., Kong, Y.: Partial saturation-aided resolution enhancement for digital holography. Appl. Opt. 57(14), 3884 (2018)CrossRefGoogle Scholar
Deka, G., Nishida, K., Mochizuki, K.: Resolution enhancement in deep-tissue nanoparticle imaging based on plasmonic saturated excitation microscopy. APL Photonics 3(3), 031301 (2018)CrossRefGoogle Scholar
Chen, S., Wang, Y.: Seismic resolution enhancement by frequency-dependent wavelet scaling. IEEE Geosci. Remote Sens. Lett. 15(5), 654–658 (2018)MathSciNetCrossRefGoogle Scholar
Lee, J.S., Kovalski, G., Sharir, T.: Advances in imaging instrumentation for nuclear cardiology. J. Nuclear Cardiol. 26(4), 1–14 (2017)Google Scholar