A survey of image registration techniques

Article Properties
Abstract
Cite
Brown, Lisa Gottesfeld. “A Survey of Image Registration Techniques”. ACM Computing Surveys, vol. 24, no. 4, 1992, pp. 325-76, https://doi.org/10.1145/146370.146374.
Brown, L. G. (1992). A survey of image registration techniques. ACM Computing Surveys, 24(4), 325-376. https://doi.org/10.1145/146370.146374
Brown LG. A survey of image registration techniques. ACM Computing Surveys. 1992;24(4):325-76.
Journal Categories
Science
Mathematics
Instruments and machines
Electronic computers
Computer science
Science
Mathematics
Instruments and machines
Electronic computers
Computer science
Computer software
Technology
Electrical engineering
Electronics
Nuclear engineering
Electronics
Computer engineering
Computer hardware
Description

Need to align images from different sources? This survey organizes and synthesizes the broad range of image registration techniques used to match two or more pictures taken at different times, from different sensors, or viewpoints. Registration is a fundamental task in image processing required by virtually all large systems that evaluate images. The paper establishes a relationship between the variations in the images and the type of registration techniques that can most appropriately be applied. The study distinguishes three major types of variations affecting image registration. It addresses variations caused by differences in acquisition, which can be removed with spatial transformations. It also considers those variations that are difficult to model, such as lighting conditions and atmospheric effects. Finally, the paper analyzes differences in images that are of interest, such as object movements or growths, which should not be removed by registration.  This framework provides a valuable resource for understanding the merits and relationships between various existing techniques and helps select the most suitable technique for a specific problem. The survey is beneficial for researchers and practitioners in fields such as computer vision, remote sensing, and medical imaging.

As a survey, this article is a strong fit for ACM Computing Surveys, which aims to provide comprehensive and structured overviews of important topics in computer science. By organizing and synthesizing the diverse techniques in image registration, the paper offers significant value to the journal’s readership, enabling them to better understand and apply these methods.

Refrences
Citations
Citations Analysis
The first research to cite this article was titled Medical image matching-a review with classification and was published in 1993. The most recent citation comes from a 2024 study titled Medical image matching-a review with classification . This article reached its peak citation in 2011 , with 80 citations.It has been cited in 552 different journals, 14% of which are open access. Among related journals, the IEEE Transactions on Image Processing cited this research the most, with 60 citations. The chart below illustrates the annual citation trends for this article.
Citations used this article by year