Multiple-image super-resolution on mobile devices: An image warping approach
This paper discusses a super-resolution (SR) system implemented on a mobile device. We utilized an Android device’s camera to take successive shots and applied a classical multiple-image super-resolution (SR) technique that utilized a set of low-resolution (LR) images. Images taken from the mobile d...
Saved in:
Main Authors: | , |
---|---|
Format: | text |
Published: |
Animo Repository
2017
|
Subjects: | |
Online Access: | https://animorepository.dlsu.edu.ph/faculty_research/3494 https://animorepository.dlsu.edu.ph/context/faculty_research/article/4496/type/native/viewcontent/s13640_016_0156_z.html |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | De La Salle University |
id |
oai:animorepository.dlsu.edu.ph:faculty_research-4496 |
---|---|
record_format |
eprints |
spelling |
oai:animorepository.dlsu.edu.ph:faculty_research-44962022-07-16T01:31:16Z Multiple-image super-resolution on mobile devices: An image warping approach Del Gallego, Neil Patrick Ilao, Joel P. This paper discusses a super-resolution (SR) system implemented on a mobile device. We utilized an Android device’s camera to take successive shots and applied a classical multiple-image super-resolution (SR) technique that utilized a set of low-resolution (LR) images. Images taken from the mobile device are subjected to our proposed filtering scheme wherein images that have noticeable presence of blur are discarded to avoid outliers from affecting the produced high-resolution (HR) image. The remaining subset of images are subjected to non-local means denoising, then feature-matched against the first reference LR image. Successive images are then aligned with respect to the first image via affine and perspective warping transformations. The LR images are then upsampled using bicubic interpolation. An L2-norm minimization approach, which is essentially taking the pixel-wise mean of the aligned images, is performed to produce the final HR image. Our study shows that our proposed method performs better than the bicubic interpolation, which makes its implementation in a mobile device quite feasible. We have also proven in our experiments that there are substantial differences from images captured using burst mode that can be utilized by an SR algorithm to create an HR image. © 2017, The Author(s). 2017-12-01T08:00:00Z text text/html https://animorepository.dlsu.edu.ph/faculty_research/3494 info:doi/10.1186/s13640-016-0156-z https://animorepository.dlsu.edu.ph/context/faculty_research/article/4496/type/native/viewcontent/s13640_016_0156_z.html Faculty Research Work Animo Repository Image registration Image processing—Digital techniques Computer Sciences Software Engineering |
institution |
De La Salle University |
building |
De La Salle University Library |
continent |
Asia |
country |
Philippines Philippines |
content_provider |
De La Salle University Library |
collection |
DLSU Institutional Repository |
topic |
Image registration Image processing—Digital techniques Computer Sciences Software Engineering |
spellingShingle |
Image registration Image processing—Digital techniques Computer Sciences Software Engineering Del Gallego, Neil Patrick Ilao, Joel P. Multiple-image super-resolution on mobile devices: An image warping approach |
description |
This paper discusses a super-resolution (SR) system implemented on a mobile device. We utilized an Android device’s camera to take successive shots and applied a classical multiple-image super-resolution (SR) technique that utilized a set of low-resolution (LR) images. Images taken from the mobile device are subjected to our proposed filtering scheme wherein images that have noticeable presence of blur are discarded to avoid outliers from affecting the produced high-resolution (HR) image. The remaining subset of images are subjected to non-local means denoising, then feature-matched against the first reference LR image. Successive images are then aligned with respect to the first image via affine and perspective warping transformations. The LR images are then upsampled using bicubic interpolation. An L2-norm minimization approach, which is essentially taking the pixel-wise mean of the aligned images, is performed to produce the final HR image. Our study shows that our proposed method performs better than the bicubic interpolation, which makes its implementation in a mobile device quite feasible. We have also proven in our experiments that there are substantial differences from images captured using burst mode that can be utilized by an SR algorithm to create an HR image. © 2017, The Author(s). |
format |
text |
author |
Del Gallego, Neil Patrick Ilao, Joel P. |
author_facet |
Del Gallego, Neil Patrick Ilao, Joel P. |
author_sort |
Del Gallego, Neil Patrick |
title |
Multiple-image super-resolution on mobile devices: An image warping approach |
title_short |
Multiple-image super-resolution on mobile devices: An image warping approach |
title_full |
Multiple-image super-resolution on mobile devices: An image warping approach |
title_fullStr |
Multiple-image super-resolution on mobile devices: An image warping approach |
title_full_unstemmed |
Multiple-image super-resolution on mobile devices: An image warping approach |
title_sort |
multiple-image super-resolution on mobile devices: an image warping approach |
publisher |
Animo Repository |
publishDate |
2017 |
url |
https://animorepository.dlsu.edu.ph/faculty_research/3494 https://animorepository.dlsu.edu.ph/context/faculty_research/article/4496/type/native/viewcontent/s13640_016_0156_z.html |
_version_ |
1767195917716291584 |