Editing Image registration (section)

== Applications ==
[[File:Mni-autoreg 03-registered.png|thumb|Registration of two [[MRI]] images of the brain]]
Image registration has applications in remote sensing (cartography updating), and computer vision.  Due to the vast range of applications to which image registration can be applied, it is impossible to develop a general method that is optimized for all uses.

[[Medical imaging|Medical image]] registration (for data of the same patient taken at different points in time such as change detection or tumor monitoring) often additionally involves ''elastic'' (also known as ''nonrigid'') registration to cope with deformation of the subject (due to breathing, anatomical changes, and so forth).<ref>{{Cite journal |last1=Zhao |first1=Shengyu |last2=Lau |first2=Tingfung |last3=Luo |first3=Ji |last4=Chang |first4=Eric I-Chao |last5=Xu |first5=Yan |year=2020 |title=Unsupervised 3D End-to-End Medical Image Registration With Volume Tweening Network |url=https://ieeexplore.ieee.org/document/8889674 |journal=IEEE Journal of Biomedical and Health Informatics |volume=24 |issue=5 |pages=1394–1404 |doi=10.1109/JBHI.2019.2951024 |pmid=31689224 |arxiv=1902.05020 |s2cid=61153704 |issn=2168-2208}}</ref><ref>{{Cite arXiv |last1=Chen |first1=Junyu |last2=He |first2=Yufan |last3=Frey |first3=Eric C. |last4=Li |first4=Ye |last5=Du |first5=Yong |date=2021-04-13 |title=ViT-V-Net: Vision Transformer for Unsupervised Volumetric Medical Image Registration |class=eess.IV |eprint=2104.06468 }}</ref><ref>{{Cite book |last1=Burduja |first1=Mihail |last2=Ionescu |first2=Radu Tudor |title=2021 IEEE International Conference on Image Processing (ICIP) |chapter=Unsupervised Medical Image Alignment with Curriculum Learning |year=2021 |chapter-url=https://ieeexplore.ieee.org/document/9506067 |pages=3787–3791 |doi=10.1109/ICIP42928.2021.9506067|arxiv=2102.10438 |isbn=978-1-6654-4115-5 |s2cid=231986287 }}</ref> Nonrigid registration of medical images can also be used to register a patient's data to an anatomical atlas, such as the [[Talairach coordinates|Talairach]] atlas for neuroimaging. In other cases, nonrigid registration is explicitly not utilized since rigid registration methods preserve the underlying geometry, e.g., in [[inner ear]] imaging.<ref name="DOI10.1038/s41598-025-90842-2">J. Gerb, V. Kirsch, E. Kierig, Thomas Brandt, Marianne Dieterich, Rainer Boegle: ''Optimizing spatial normalization of multisubject inner ear MRI: comparison of different geometry-preserving co-registration approaches.'' In: ''Scientific Reports.'' 2025, Band 15, Nummer 1 {{DOI|10.1038/s41598-025-90842-2}}.</ref>

In [[Radiation therapy]] rigid image registration (RIR) is a fundamental element in most imaging software systems. It involves aligning images by applying translational and rotational adjustments, up to a six degrees of freedom—three for translation along the x, y, and z axes, and three for rotation about these axes. RIR aligns images appropriately using these six parameters, allowing for precise treatment planning and delivery.<ref>{{Cite journal |last=Yuen |first=Johnson |last2=Barber |first2=Jeffrey |last3=Ralston |first3=Anna |last4=Gray |first4=Alison |last5=Walker |first5=Amy |last6=Hardcastle |first6=Nicholas |last7=Schmidt |first7=Laurel |last8=Harrison |first8=Kristie |last9=Poder |first9=Joel |last10=Sykes |first10=Jonathan R. |last11=Jameson |first11=Michael G. |date=2020 |title=An international survey on the clinical use of rigid and deformable image registration in radiotherapy |url=https://aapm.onlinelibrary.wiley.com/doi/10.1002/acm2.12957 |journal=Journal of Applied Clinical Medical Physics |language=en |volume=21 |issue=10 |pages=10–24 |doi=10.1002/acm2.12957 |issn=1526-9914 |pmc=7075391 |pmid=32915492}}</ref> 

In [[astrophotography]], image alignment and stacking are often used to increase the signal to noise ratio for faint objects. Without stacking it may be used to produce a timelapse of events such as a planet's rotation of a transit across the Sun.  Using control points (automatically or manually entered), the computer performs transformations on one image to make major features align with a second or multiple images. This technique may also be used for images of different sizes, to allow images taken through different telescopes or lenses to be combined.

In [[cryo-TEM]], instability causes specimen drift and many fast acquisitions with accurate image registration is required to preserve high resolution and obtain high signal to noise images. For low SNR data, the best image registration is achieved by cross-correlating all permutations of images in an image stack.<ref name=Savitsky>{{cite journal|title=Image registration of low signal-to-noise cryo-STEM data|year=2018|author1=Savitsky |author2=El Baggari |author3=Clement |author4=Hovden |author5=Kourkoutis |journal=Ultramicroscopy|volume=191|pages=56–65|doi=10.1016/j.ultramic.2018.04.008|pmid=29843097|arxiv=1710.09281|s2cid=26983019}}</ref>

Image registration is an essential part of panoramic image creation. There are many different techniques that can be implemented in real time and run on embedded devices like cameras and camera-phones.