An Algorithm for image stitching and blending
Open accessAbstract
In many clinical studies, including those of cancer, it is highly desirable to acquire images of whole tumour sections whilst retaining a microscopic resolution. A usual approach to this is to create a composite image by appropriately overlapping individual images acquired at high magnification under a microscope. A mosaic of these images can be accurately formed by applying image registration, overlap removal and blending techniques. We describe an optimised, automated, fast and reliable method for both image joining and blending. These algorithms can be applied to most types of light microscopy imaging. Examples from histology, from in vivo vascular imaging and from fluorescence applications are shown, both in 2D and 3D. The algorithms are robust to the varying image overlap of a manually moved stage, though examples of composite images acquired both with manually-driven and computer-controlled stages are presented. The overlap-removal algorithm is based on the cross-correlation method; this is used to determine and select the best correlation point between any new image and the previous composite image. A complementary image blending algorithm, based on a gradient method, is used to eliminate sharp intensity changes at the image joins, thus gradually blending one image onto the adjacent 'composite'. The details of the algorithm to overcome both intensity discrepancies and geometric misalignments between the stitched images will be presented and illustrated with several examples.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
A gradient-mixing method was chosen for stitching because of its simplicity in implementation and more hidden stitch than in alpha-channel approach.
“A gradient-mixing [12] method was chosen for stitching because of its simplicity in implementation and more hidden stitch than in alpha-channel approach.”
From Real-time system for automatic cold strip surface defect detection (2019) · cites this paper as [12]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
A survey of image registration techniques
Brown, L. G. (1992) · ACM Computing Surveys · doi:10.1145/146370.146374 · Cited by 4,079 · see citing works
Chen, S. E. (1995) · ACM SIGGRAPH Annual Conference on Computer Graphics and Interactive Techniques (SIGGRAPH) · doi:10.1145/218380.218395 · Cited by 1,162 · see citing works
Video mosaics for virtual environments
Szeliski, R. (1996) · IEEE Computer Graphics and Applications · doi:10.1109/38.486677 · Cited by 728 · see citing works
Seamless Image Stitching in the Gradient Domain
Levin, A., Zomet, A., Peleg, B., et al. (2004) · Lecture notes in computer science · doi:10.1007/978-3-540-24673-2_31 · Cited by 514 · see citing works
Efficient View-Dependent Image-Based Rendering with Projective Texture-Mapping
Debevec, P. E., Yu, Y., & Borshukov, G. (1998) · Eurographics · doi:10.1007/978-3-7091-6453-2_10 · Cited by 490 · see citing works
IEEE Computer Graphics and Applications
(2020) · IEEE Micro · doi:10.1109/mm.2020.2996321 · Cited by 398 · see citing works
Eliminating ghosting and exposure artifacts in image mosaics
Uyttendaele, M., Eden, A., & Skeliski, R. (2005) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2001.991005 · Cited by 339 · see citing works
Tozer, G. M., Prise, V. E., Wilson, J., Čemažar, M., Shan, S., Dewhirst, M. W., Barber, P. R., Vojnovic, B., & Chaplin, D. J. (2001) · PubMed · Cited by 283 · see citing works
Self-citationFluorescence techniques for drug delivery research: theory and practice
White, N. S. (2004) · Advanced Drug Delivery Reviews · doi:10.1016/j.addr.2004.08.003 · Cited by 112 · see citing works
Blending Images for Texturing 3D Models
Baumberg, A. (2002) · British Machine Vision Conference (BMVC) · doi:10.5244/c.16.38 · Cited by 98 · see citing works
Image Stitching — Comparisons and New Techniques
Chen, C., & Klette, R. (1999) · Lecture notes in computer science · doi:10.1007/3-540-48375-6_73 · Cited by 79 · see citing works
Fast stitching algorithm for moving object detection and mosaic construction
Hsieh, J.-W. (2004) · Image and Vision Computing · doi:10.1016/j.imavis.2003.09.018 · Cited by 60 · see citing works
Computer Analysis of Images and Patterns
Azzopardi, G., & Petkov, N. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-23192-1 · Cited by 54 · see citing works
Image mosaicing by stratified matching
Kanazawa, Y., & Kanatani, K. (2003) · Image and Vision Computing · doi:10.1016/j.imavis.2003.07.001 · Cited by 46 · see citing works
A Fast Method for Image Mosaicing using Geometric Hashing
Bhosle, U., Chaudhuri, S., & Roy, S. D. (2002) · IETE Journal of Research · doi:10.1080/03772063.2002.11416292 · Cited by 30 · see citing works
Multi-resolution image registration using genetics
Chalermwat, P., & El‐Ghazawi, T. (1999) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.1999.822937 · Cited by 28 · see citing works
Imaging protein-protein interactions by multiphoton FLIM
Ameer‐Beg, S., Edme, N., Peter, M., et al. (2003) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.500544 · Cited by 18 · see citing works
Fast stitching algorithm for moving object detection and mosaic construction
Hsieh, J.-W. (2003) · doi:10.1109/icme.2003.1220860 · Cited by 5 · see citing works
Imaging Protein-Protein Interactions By Multiphoton FLIM
Ameer‐Beg, S., Edme, N., Peter, M., et al. (2003) · doi:10.1364/ecbo.2003.5139_180 · Cited by 1 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Real-time system for automatic cold strip surface defect detection
Kostenetskiy, P., Alkapov, R., Vetoshkin, N., Chulkevich, R., Napolskikh, I., & Poponin, O. (2019) · FME Transactions · doi:10.5937/fmet1904765k · Cited by 23 · see citing works
- Authors
- Rankov, V., Locke, R. J., Edens, R. J., Barber, P. R., & Vojnovic, B.
- Affiliations
- Mount Vernon Hospital (GB)
- Venue
- SPIE Proceedings
- Publisher
- SPIE
- Published
- 2005-03-24
- Volume
- 5701
- Pages
- 190
- ISSN
- 0277-786X (ISSN-L)
- OpenAlex
- W2043171920
- Cited by
- 114
- References
- 19
- Citations by year
- 2026: 4 · 2025: 2 · 2024: 6 · 2023: 6 · 2022: 3 · 2021: 5 · 2020: 2 · 2019: 9 · 2018: 7 · 2017: 5 · 2016: 5 · 2015: 6 · 2014: 4 · 2013: 7 · 2012: 12
- FWCI
- 6.94
- Type
- conference paper
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE (publishedVersion)
- REDUN - Repository of the EDUCONS University (submittedVersion, cc-by)
- Funders
- Cancer Research UK
- Topics
- Physical Sciences › Engineering › Media Technology › Advanced Image Fusion Techniques
- Physical Sciences › Engineering › Media Technology › Image Processing Techniques and Applications
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Biophysics › Cell Image Analysis Techniques
- Keywords
- image stitching, image blending, image registration, overlap removal, cross correlation function, optical microscopy, histology, in vivo vascular imaging, fluorescence imaging, 3D image reconstruction, tumor imaging, geometric misalignment
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
