Abstract
The subpixel-shifted (SPS) images acquisition method based on imaging system has the limitations of complex structure, difficult production and high cost. Therefore, this paper proposes an image super-resolution reconstruction method based on registration. In the first phase, the registration algorithm is used to select the SPS images. In order to improve the accuracy of the registration algorithm, a registration algorithm combining SIFT-FLANN and misregistration points elimination (SFME) is proposed. In the second phase, an interpolation of nonuniformly spaced samples based on pixel gray correction is proposed to get the high resolution (HR) image. Experiments show that the images selection method can obtain higher-precision SPS images, and the reconstruction method can reconstruct HR image with better visual and higher spatial resolution. Finally, the image magnification factor and the number of SPS images used in the reconstruction process are analyzed to describe the practical application value of the methods proposed in this paper.
Highlights
A clear image Super-resolution (SR) [1]–[3], [34] technology is of critical importance in such numerous areas of image processing applications as security, surveillance, military reconnaissance and medical imaging
We present an images super-resolution reconstruction method based on registration, which comprises two phases: images selection and image reconstruction: (i) In the images selection phase, a registration algorithm combining SIFT-FLANN with misregistration points elimination is proposed to select the desired frames. (ii) In the image reconstruction phase, when the subpixel-shifted images are given, the interpolation of nonuniformly spaced samples based on region point correction is proposed to reconstruct the high resolution (HR) image
In this paper, for image acquisition we propose a SPS images selection method based on SIFT-FLANN and misregistration points elimination (SFME) registration algorithm, which does not rely on the special imaging system, and has the advantages of simple implementation and low cost
Summary
A clear image Super-resolution (SR) [1]–[3], [34] technology is of critical importance in such numerous areas of image processing applications as security, surveillance, military reconnaissance and medical imaging. The goal of SR is to enhance a low resolution (LR) image to higher resolution by filling missing fine details in the LR image. This field can be divided into Single-Image SR (SISR) and Multi-Image SR (MISR) the focus of this paper. Note that most of the recent SISR methods fall into the example based methods which try to learn prior knowledge from LR and HR pairs, alleviating the illposedness of SISR. With the rapid development of deep learning techniques in recent years, it has a wide range of applications in the fields of image segmentation [32], recognition [33] and image style transfer [35]. Deep learning based SR models have been actively explored and
Sign-in/Register to view highlights & summary 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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
