The Application of Supervised Machine Learning Algorithms for Image Alignment in Multi-Channel Imaging Systems
Kyrylo Romanenko,
Yevgen Oberemok,
Ivan Syniavskyi,
Natalia Bezugla,
Pawel Komada,
Mykhailo Bezuglyi
Affiliations
Kyrylo Romanenko
Department 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, Ukraine
Yevgen Oberemok
Department of Quantum Radiophysics and Nanoelectronics, Taras Shevchenko National University of Kyiv, 60 Volodymyrska St., 01033 Kyiv, Ukraine
Ivan Syniavskyi
Department 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, Ukraine
Natalia Bezugla
Department 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, Ukraine
Pawel Komada
Department of Electronics and Information Techniques, Faculty of Electrical Engineering and Computer Science, Lublin University of Technology, 38D Nadbystrzycka Street, 20-618 Lublin, Poland
Mykhailo Bezuglyi
Department 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, Ukraine
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.
