An MCMC Approach to Bayesian Image Analysis in Fourier Space
Bayesian image analysis methods are commonly applied to solve image analysis problems such as noise reduction, feature enhancement, and object detection. A primary limitation of these methods is their computational cost due to the complex joint interdependencies between pixels, which limits the effi...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2025-12-01
|
| Series: | Data Science in Science |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/26941899.2025.2452603 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832593380387848192 |
|---|---|
| author | Konstantinos Bakas John Kornak Hernando Ombao |
| author_facet | Konstantinos Bakas John Kornak Hernando Ombao |
| author_sort | Konstantinos Bakas |
| collection | DOAJ |
| description | Bayesian image analysis methods are commonly applied to solve image analysis problems such as noise reduction, feature enhancement, and object detection. A primary limitation of these methods is their computational cost due to the complex joint interdependencies between pixels, which limits the efficiency of performing posterior sampling through Markov chain Monte Carlo (MCMC). To alleviate this problem, we develop a new posterior sampling method based on modeling the prior and likelihood in the space of the Fourier transform of the image. One advantage of Fourier-based methods is that a large set of spatially correlated processes in image space can be represented via independent processes over Fourier space. A recent approach, Bayesian Image Analysis in Fourier Space (BIFS), introduced parameter functions to describe prior expectations about distributional parameters over Fourier space. To date, BIFS has relied on Maximum a Posteriori (MAP) estimation. This work extends BIFS to an MCMC approach, allowing a range of posterior estimators, including credible intervals and posterior probability maps. The computational efficiency of MCMC for BIFS is much improved over conventional Bayesian image analysis, and mixing concerns that are ubiquitous in high-dimensional MCMC sampling problems are avoided. |
| format | Article |
| id | doaj-art-31028554024e44dfb1e67e13d96da554 |
| institution | Kabale University |
| issn | 2694-1899 |
| language | English |
| publishDate | 2025-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Data Science in Science |
| spelling | doaj-art-31028554024e44dfb1e67e13d96da5542025-01-20T17:48:36ZengTaylor & Francis GroupData Science in Science2694-18992025-12-014110.1080/26941899.2025.2452603An MCMC Approach to Bayesian Image Analysis in Fourier SpaceKonstantinos Bakas0John Kornak1Hernando Ombao2Statistics Program, King Abdullah University of Science and Technology, Thuwal, Saudi ArabiaDepartment of Epidemiology and Biostatistics, University of California, San Francisco, CA, USAStatistics Program, King Abdullah University of Science and Technology, Thuwal, Saudi ArabiaBayesian image analysis methods are commonly applied to solve image analysis problems such as noise reduction, feature enhancement, and object detection. A primary limitation of these methods is their computational cost due to the complex joint interdependencies between pixels, which limits the efficiency of performing posterior sampling through Markov chain Monte Carlo (MCMC). To alleviate this problem, we develop a new posterior sampling method based on modeling the prior and likelihood in the space of the Fourier transform of the image. One advantage of Fourier-based methods is that a large set of spatially correlated processes in image space can be represented via independent processes over Fourier space. A recent approach, Bayesian Image Analysis in Fourier Space (BIFS), introduced parameter functions to describe prior expectations about distributional parameters over Fourier space. To date, BIFS has relied on Maximum a Posteriori (MAP) estimation. This work extends BIFS to an MCMC approach, allowing a range of posterior estimators, including credible intervals and posterior probability maps. The computational efficiency of MCMC for BIFS is much improved over conventional Bayesian image analysis, and mixing concerns that are ubiquitous in high-dimensional MCMC sampling problems are avoided.https://www.tandfonline.com/doi/10.1080/26941899.2025.2452603Bayesian image analysisMarkov chain Monte Carlok-spacestatistical image analysis |
| spellingShingle | Konstantinos Bakas John Kornak Hernando Ombao An MCMC Approach to Bayesian Image Analysis in Fourier Space Data Science in Science Bayesian image analysis Markov chain Monte Carlo k-space statistical image analysis |
| title | An MCMC Approach to Bayesian Image Analysis in Fourier Space |
| title_full | An MCMC Approach to Bayesian Image Analysis in Fourier Space |
| title_fullStr | An MCMC Approach to Bayesian Image Analysis in Fourier Space |
| title_full_unstemmed | An MCMC Approach to Bayesian Image Analysis in Fourier Space |
| title_short | An MCMC Approach to Bayesian Image Analysis in Fourier Space |
| title_sort | mcmc approach to bayesian image analysis in fourier space |
| topic | Bayesian image analysis Markov chain Monte Carlo k-space statistical image analysis |
| url | https://www.tandfonline.com/doi/10.1080/26941899.2025.2452603 |
| work_keys_str_mv | AT konstantinosbakas anmcmcapproachtobayesianimageanalysisinfourierspace AT johnkornak anmcmcapproachtobayesianimageanalysisinfourierspace AT hernandoombao anmcmcapproachtobayesianimageanalysisinfourierspace AT konstantinosbakas mcmcapproachtobayesianimageanalysisinfourierspace AT johnkornak mcmcapproachtobayesianimageanalysisinfourierspace AT hernandoombao mcmcapproachtobayesianimageanalysisinfourierspace |