The Application of Supervised Machine Learning Algorithms for Image Alignment in Multi-Channel Imaging Systems
This study presents a method for aligning the geometric parameters of images in multi-channel imaging systems based on the application of pre-processing methods, machine learning algorithms, and a calibration setup using an array of orderly markers at the nodes of an imaginary grid. According to the...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/2/544 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832587534846132224 |
|---|---|
| author | Kyrylo Romanenko Yevgen Oberemok Ivan Syniavskyi Natalia Bezugla Pawel Komada Mykhailo Bezuglyi |
| author_facet | Kyrylo Romanenko Yevgen Oberemok Ivan Syniavskyi Natalia Bezugla Pawel Komada Mykhailo Bezuglyi |
| author_sort | Kyrylo Romanenko |
| collection | DOAJ |
| description | This study presents a method for aligning the geometric parameters of images in multi-channel imaging systems based on the application of pre-processing methods, machine learning algorithms, and a calibration setup using an array of orderly markers at the nodes of an imaginary grid. According to the proposed method, one channel of the system is used as a reference. The images from the calibration setup in each channel determine the coordinates of the markers, and the displacements of the marker centers in the system’s channels relative to the coordinates of the centers in the reference channel are then determined. Correction models are obtained as multiple polynomial regression models based on these displacements. These correction models align the geometric parameters of the images in the system channels before they are used in the calculations. The models are derived once, allowing for geometric calibration of the imaging system. The developed method is applied to align the images in the channels of a module of a multispectral imaging polarimeter. As a result, the standard image alignment error in the polarimeter channels is reduced from 4.8 to 0.5 pixels. |
| format | Article |
| id | doaj-art-e7b308daf14948e599646181eece9b31 |
| institution | Kabale University |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-e7b308daf14948e599646181eece9b312025-01-24T13:49:18ZengMDPI AGSensors1424-82202025-01-0125254410.3390/s25020544The Application of Supervised Machine Learning Algorithms for Image Alignment in Multi-Channel Imaging SystemsKyrylo Romanenko0Yevgen Oberemok1Ivan Syniavskyi2Natalia Bezugla3Pawel Komada4Mykhailo Bezuglyi5Department of Computer-Integrated Technologies of Device Production, Faculty of Instrumentation Engineering, National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute”, Beresteiskyi Ave., 37, 03056 Kyiv, UkraineDepartment of Quantum Radiophysics and Nanoelectronics, Taras Shevchenko National University of Kyiv, 60 Volodymyrska St., 01033 Kyiv, UkraineDepartment of Computer-Integrated Technologies of Device Production, Faculty of Instrumentation Engineering, National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute”, Beresteiskyi Ave., 37, 03056 Kyiv, UkraineDepartment of Computer-Integrated Technologies of Device Production, Faculty of Instrumentation Engineering, National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute”, Beresteiskyi Ave., 37, 03056 Kyiv, UkraineDepartment of Electronics and Information Techniques, Faculty of Electrical Engineering and Computer Science, Lublin University of Technology, 38D Nadbystrzycka Street, 20-618 Lublin, PolandDepartment of Computer-Integrated Technologies of Device Production, Faculty of Instrumentation Engineering, National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute”, Beresteiskyi Ave., 37, 03056 Kyiv, UkraineThis study presents a method for aligning the geometric parameters of images in multi-channel imaging systems based on the application of pre-processing methods, machine learning algorithms, and a calibration setup using an array of orderly markers at the nodes of an imaginary grid. According to the proposed method, one channel of the system is used as a reference. The images from the calibration setup in each channel determine the coordinates of the markers, and the displacements of the marker centers in the system’s channels relative to the coordinates of the centers in the reference channel are then determined. Correction models are obtained as multiple polynomial regression models based on these displacements. These correction models align the geometric parameters of the images in the system channels before they are used in the calculations. The models are derived once, allowing for geometric calibration of the imaging system. The developed method is applied to align the images in the channels of a module of a multispectral imaging polarimeter. As a result, the standard image alignment error in the polarimeter channels is reduced from 4.8 to 0.5 pixels.https://www.mdpi.com/1424-8220/25/2/544geometric calibrationmulti-channel imaging systemsimage processingimage analysisimage alignmentmachine learning algorithms |
| spellingShingle | Kyrylo Romanenko Yevgen Oberemok Ivan Syniavskyi Natalia Bezugla Pawel Komada Mykhailo Bezuglyi The Application of Supervised Machine Learning Algorithms for Image Alignment in Multi-Channel Imaging Systems Sensors geometric calibration multi-channel imaging systems image processing image analysis image alignment machine learning algorithms |
| title | The Application of Supervised Machine Learning Algorithms for Image Alignment in Multi-Channel Imaging Systems |
| title_full | The Application of Supervised Machine Learning Algorithms for Image Alignment in Multi-Channel Imaging Systems |
| title_fullStr | The Application of Supervised Machine Learning Algorithms for Image Alignment in Multi-Channel Imaging Systems |
| title_full_unstemmed | The Application of Supervised Machine Learning Algorithms for Image Alignment in Multi-Channel Imaging Systems |
| title_short | The Application of Supervised Machine Learning Algorithms for Image Alignment in Multi-Channel Imaging Systems |
| title_sort | application of supervised machine learning algorithms for image alignment in multi channel imaging systems |
| topic | geometric calibration multi-channel imaging systems image processing image analysis image alignment machine learning algorithms |
| url | https://www.mdpi.com/1424-8220/25/2/544 |
| work_keys_str_mv | AT kyryloromanenko theapplicationofsupervisedmachinelearningalgorithmsforimagealignmentinmultichannelimagingsystems AT yevgenoberemok theapplicationofsupervisedmachinelearningalgorithmsforimagealignmentinmultichannelimagingsystems AT ivansyniavskyi theapplicationofsupervisedmachinelearningalgorithmsforimagealignmentinmultichannelimagingsystems AT nataliabezugla theapplicationofsupervisedmachinelearningalgorithmsforimagealignmentinmultichannelimagingsystems AT pawelkomada theapplicationofsupervisedmachinelearningalgorithmsforimagealignmentinmultichannelimagingsystems AT mykhailobezuglyi theapplicationofsupervisedmachinelearningalgorithmsforimagealignmentinmultichannelimagingsystems AT kyryloromanenko applicationofsupervisedmachinelearningalgorithmsforimagealignmentinmultichannelimagingsystems AT yevgenoberemok applicationofsupervisedmachinelearningalgorithmsforimagealignmentinmultichannelimagingsystems AT ivansyniavskyi applicationofsupervisedmachinelearningalgorithmsforimagealignmentinmultichannelimagingsystems AT nataliabezugla applicationofsupervisedmachinelearningalgorithmsforimagealignmentinmultichannelimagingsystems AT pawelkomada applicationofsupervisedmachinelearningalgorithmsforimagealignmentinmultichannelimagingsystems AT mykhailobezuglyi applicationofsupervisedmachinelearningalgorithmsforimagealignmentinmultichannelimagingsystems |