Russian Federation
Russian Federation
Russian Federation
Russian Federation
In this study, we have developed a new image enhancement method that uses fuzzy logic. This method allows us to split pixel values into different levels of importance, which helps to compensate for the loss of local brightness in dark and bright areas of an image. The goal is to increase the overall brightness of the image while preserving details. The process involves three stages. Firstly, the satellite image is transformed into a membership space using the c-means clustering algorithm. This creates a model that can be used to convert each pixel value into a level of importance. Secondly, a corresponding model is created for each level of importance based on the membership data. Finally, the image is transformed back into a standard brightness space by combining the grayscale values for each level. Our results show that this method improves the visual quality and accuracy of measurements when compared to traditional methods.
image, processing, color, interpretation, fuzzy logic
1. Polesel A., Ramponi G., Mathews V.J. Image enhancement via adaptive unsharp masking // IEEE transactions on image processing. 2000. Vol. 9. № 3. P. 505–510. DOI:https://doi.org/10.1109/83.826787.
2. Nasu Iu., Lanin V.V. Development of Legal Document Classification System Based on Support Vector Machine // Proceedings of the Institute for System Programming of the RAS. 2023. Vol. 35. № 2. P. 49–56. DOI:https://doi.org/10.15514/ISPRAS-2023-35(2)-4. EDN NKCHIR.
3. Mihajlyuk Yu.P., Nacharov D.V. Apparatnaya realizaciya metoda povysheniya razlichimosti ob"ektov na izobrazheniyah putyom normalizacii gistogrammy yarkosti // Vestnik Povolzhskogo gosudarstvennogo tekhnologicheskogo universiteta. Ser.: Radiotekhnicheskie i infokommunikacionnye sistemy. 2023. № 2 (58). S. 27–43. DOI:https://doi.org/10.25686/2306-2819.2023.2.27. EDN IHICQM.
4. Bassel' Z. Primenenie metoda opornyh vektorov i gistogramm napravlennyh gradientov dlya klassifikacii sobytij na izobrazheniyah // Obrazovanie, nauka, proizvodstvo. Belgorod: Belgorodskij gos. tekhnol. un-t im. V.G. Shuhova, 2015. S. 2652–2659. EDN VNPITN.
5. Rauhvarger A.B., Poshekhonov N.A. Privedenie gistogrammy yarkosti slabokontrastnyh cifrovyh izobrazhenij k dvuhurovnevomu kusochno-ravnomernomu raspredeleniyu // Vestnik Astrahanskogo gosudarstvennogo tekhnicheskogo universiteta. Ser.: Upravlenie, vychislitel'naya tekhnika i informatika. 2020. № 1. S. 57–63. DOI:https://doi.org/10.24143/2072-9502-2020-1-57-63. EDN JQBJIU.
6. Zadeh L.A. Zadeh, Fzzy sets // Fuzzy sets, fuzzy logic, and fuzzy systems. 1965. P. 19–34.
7. Kalkabekova T.Zh. Analysİs of clusterİng methods and modellİng a clusterİng data network // Energetika, infokommunikacionnye tekhnologii i vysshee obrazovanie: sb. nauch. statej po materialam Mezhdunar. konf: v 3-h t. Kazan': Kazanskij gos. energeticheskij un-t, 2023. T. 3. P. 53–62. EDN ZBSLCK.
8. Bezdek J.C., Bezdek J.C. Objective function clustering // Pattern recognition with fuzzy objective function algorithms. 1981. P. 43–93. DOI:https://doi.org/10.1007/978-1-4757-0450-1_3.
9. Ross M. Segment cluster tracking // Conference on Colour in Graphics, Imaging, and Vision. Society of Imaging Science and Technology. 2004. Vol. 2. P. 130–134.
10. Segmentation of Images Used in Unmanned Aerial Vehicles Navigation Systems / N. Yeromina [et al.] // Problems of the Regional Energetics. 2023. № 4 (60). P. 30–42. DOI:https://doi.org/10.52254/1857-0070.2023.4-60.03. EDN GBQPEW.
11. Iskra N.A., Iskra V., Lukashevich M. Neural network based image understanding with ontological approach // Otkrytye semanticheskie tekhnologii proektirovaniya intellektual'nyh sistem. 2019. № 3. P. 113–122. EDN DVIKMR.
12. Sazonov V.V. Nelinejnaya SVD-faktorizaciya v zadache povysheniya kontrastnosti izobrazhenij // Problemy avtomatizacii i upravleniya v tekhnicheskih sistemah: sb. nauch. statej XXXV Vseros. s mezhdunar. uchastiem nauch.-tekhn. konf., posvyashch. 80-letiyu Penzenskogo gos. un-ta: v 2-h t. Penza: Penzenskij gos. un-t, 2023. S. 229–233. EDN BBBPNI.
13. Nill N.B., Bouzas B. Objective image quality measure derived from digital image power spectra // Optical engineering. 1992. Vol. 31. № 4. P. 813–825. DOI:https://doi.org/10.1117/12.56114.
14. Tumko V.V., Nacharov D.V., Mihajlyuk Yu.P. Metod povysheniya kachestva izobrazheniya posredstvom normalizacii gistogrammy yarkosti // SVCH-tekhnika i telekommunikacionnye tekhnologii (KryMiKo'2018): materialy 28-j Mezhdunar. Krymskoj konf. M.; Minsk; Sevastopol': Sevastopol'skij gos. un-t, 2018. T. 2. S. 420–426. EDN YQEUCT.
