Zernike Moment Based Classification of Cosmic Ray Candidate Hits from CMOS Sensors
Reliable tools for artefact rejection and signal classification are a must for cosmic ray detection experiments based on CMOS technology. In this paper, we analyse the fitness of several feature-based statistical classifiers for the classification of particle candidate hits in four categories: spots...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/22/7718 |
| _version_ | 1797508479329501184 |
|---|---|
| author | Olaf Bar Łukasz Bibrzycki Michał Niedźwiecki Marcin Piekarczyk Krzysztof Rzecki Tomasz Sośnicki Sławomir Stuglik Michał Frontczak Piotr Homola David E. Alvarez-Castillo Thomas Andersen Arman Tursunov |
| author_facet | Olaf Bar Łukasz Bibrzycki Michał Niedźwiecki Marcin Piekarczyk Krzysztof Rzecki Tomasz Sośnicki Sławomir Stuglik Michał Frontczak Piotr Homola David E. Alvarez-Castillo Thomas Andersen Arman Tursunov |
| author_sort | Olaf Bar |
| collection | DOAJ |
| description | Reliable tools for artefact rejection and signal classification are a must for cosmic ray detection experiments based on CMOS technology. In this paper, we analyse the fitness of several feature-based statistical classifiers for the classification of particle candidate hits in four categories: spots, tracks, worms and artefacts. We use Zernike moments of the image function as feature carriers and propose a preprocessing and denoising scheme to make the feature extraction more efficient. As opposed to convolution neural network classifiers, the feature-based classifiers allow for establishing a connection between features and geometrical properties of candidate hits. Apart from basic classifiers we also consider their ensemble extensions and find these extensions generally better performing than basic versions, with an average recognition accuracy of 88%. |
| first_indexed | 2024-03-10T05:04:34Z |
| format | Article |
| id | doaj.art-e0d447a779a44da8978b952d679c1456 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T05:04:34Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-e0d447a779a44da8978b952d679c14562023-11-23T01:28:37ZengMDPI AGSensors1424-82202021-11-012122771810.3390/s21227718Zernike Moment Based Classification of Cosmic Ray Candidate Hits from CMOS SensorsOlaf Bar0Łukasz Bibrzycki1Michał Niedźwiecki2Marcin Piekarczyk3Krzysztof Rzecki4Tomasz Sośnicki5Sławomir Stuglik6Michał Frontczak7Piotr Homola8David E. Alvarez-Castillo9Thomas Andersen10Arman Tursunov11Institute of Computer Science, Pedagogical University of Krakow, 30-084 Kraków, PolandInstitute of Computer Science, Pedagogical University of Krakow, 30-084 Kraków, PolandDepartment of Computer Science, Cracow University of Technology, 31-155 Kraków, PolandInstitute of Computer Science, Pedagogical University of Krakow, 30-084 Kraków, PolandDepartment of Biocybernetics and Biomedical Engineering, AGH University of Science and Technology, 30-059 Kraków, PolandDepartment of Biocybernetics and Biomedical Engineering, AGH University of Science and Technology, 30-059 Kraków, PolandInstitute of Nuclear Physics, Polish Academy of Sciences, 31-342 Kraków, PolandInstitute of Computer Science, Pedagogical University of Krakow, 30-084 Kraków, PolandInstitute of Nuclear Physics, Polish Academy of Sciences, 31-342 Kraków, PolandInstitute of Nuclear Physics, Polish Academy of Sciences, 31-342 Kraków, PolandNSCIR, Thornbury, ON N0H2P0, CanadaInstitute of Physics, Silesian University in Opava, Bezručovo nám 13, 74601 Opava, Czech RepublicReliable tools for artefact rejection and signal classification are a must for cosmic ray detection experiments based on CMOS technology. In this paper, we analyse the fitness of several feature-based statistical classifiers for the classification of particle candidate hits in four categories: spots, tracks, worms and artefacts. We use Zernike moments of the image function as feature carriers and propose a preprocessing and denoising scheme to make the feature extraction more efficient. As opposed to convolution neural network classifiers, the feature-based classifiers allow for establishing a connection between features and geometrical properties of candidate hits. Apart from basic classifiers we also consider their ensemble extensions and find these extensions generally better performing than basic versions, with an average recognition accuracy of 88%.https://www.mdpi.com/1424-8220/21/22/7718CMOS sensorsfeature-based classificationZernike momentsmachine learningcomputer vision |
| spellingShingle | Olaf Bar Łukasz Bibrzycki Michał Niedźwiecki Marcin Piekarczyk Krzysztof Rzecki Tomasz Sośnicki Sławomir Stuglik Michał Frontczak Piotr Homola David E. Alvarez-Castillo Thomas Andersen Arman Tursunov Zernike Moment Based Classification of Cosmic Ray Candidate Hits from CMOS Sensors Sensors CMOS sensors feature-based classification Zernike moments machine learning computer vision |
| title | Zernike Moment Based Classification of Cosmic Ray Candidate Hits from CMOS Sensors |
| title_full | Zernike Moment Based Classification of Cosmic Ray Candidate Hits from CMOS Sensors |
| title_fullStr | Zernike Moment Based Classification of Cosmic Ray Candidate Hits from CMOS Sensors |
| title_full_unstemmed | Zernike Moment Based Classification of Cosmic Ray Candidate Hits from CMOS Sensors |
| title_short | Zernike Moment Based Classification of Cosmic Ray Candidate Hits from CMOS Sensors |
| title_sort | zernike moment based classification of cosmic ray candidate hits from cmos sensors |
| topic | CMOS sensors feature-based classification Zernike moments machine learning computer vision |
| url | https://www.mdpi.com/1424-8220/21/22/7718 |
| work_keys_str_mv | AT olafbar zernikemomentbasedclassificationofcosmicraycandidatehitsfromcmossensors AT łukaszbibrzycki zernikemomentbasedclassificationofcosmicraycandidatehitsfromcmossensors AT michałniedzwiecki zernikemomentbasedclassificationofcosmicraycandidatehitsfromcmossensors AT marcinpiekarczyk zernikemomentbasedclassificationofcosmicraycandidatehitsfromcmossensors AT krzysztofrzecki zernikemomentbasedclassificationofcosmicraycandidatehitsfromcmossensors AT tomaszsosnicki zernikemomentbasedclassificationofcosmicraycandidatehitsfromcmossensors AT sławomirstuglik zernikemomentbasedclassificationofcosmicraycandidatehitsfromcmossensors AT michałfrontczak zernikemomentbasedclassificationofcosmicraycandidatehitsfromcmossensors AT piotrhomola zernikemomentbasedclassificationofcosmicraycandidatehitsfromcmossensors AT davidealvarezcastillo zernikemomentbasedclassificationofcosmicraycandidatehitsfromcmossensors AT thomasandersen zernikemomentbasedclassificationofcosmicraycandidatehitsfromcmossensors AT armantursunov zernikemomentbasedclassificationofcosmicraycandidatehitsfromcmossensors |