SUN’IY INTELLEKTDA TASVIR SEGMENTATSIYA ANIQLIGINI OSHIRUVCHI GRABCUT ALGORITMI TAHLILI
DOI:
https://doi.org/10.65164/k96nh869Ключевые слова:
GrabCut, segmentatsiya, foreground, threshold, robustness, Region of Interest, Gaussian Mixture Models, Gibbs , smoothness termАннотация
Ushbu maqolada tasvirlarni qayta ishlash sohasida keng qo‘llaniladigan
GrabCut segmentatsiya algoritmining ishlash prinsipi va samaradorligi tahlil qilingan. Masala graf
nazariyasiga asoslangan yondashuv doirasida ko‘rib chiqilib, algoritmning energiya funksiyasi,
hududiy ma’lumotlar hadi va silliqlash hadi matematik jihatdan ifodalangan. Tasvirning rang va
chegara ma’lumotlarini hisobga olgan holda, old fon va orqa fonni ajratish jarayoni iterativ
optimallashtirish asosida amalga oshirilgan. Maqolada GrabCut algoritmining klassik varianti
hamda uning hisoblash vaqtini kamaytirishga qaratilgan takomillashtirilgan yondashuvlari tahlil
qilingan. Olingan natijalar murakkab fonli tasvirlarda segmentatsiya aniqligi va hisoblash
samaradorligini oshirish imkonini berishini ko‘rsatadi
Библиографические ссылки
1. Han, S.; Wang, L. Overview of Threshold Methods for Image Segmentation. Syst. Eng.
Electron. Technol. 2022,102, 91–94.
2. Jiang, F.; Gu, Q.; Hao, H. Overview of Content based Image Segmentation Methods. J.
Softw. 2017,28, 160–183.
3. Hao, Q.; Zheng, W.; Wang, C.; Xiao, Y.; Zhang, L. MLRN: A multiview local
reconstruction network for single image restoration.
4. Inf. Process. Manag. 2024,61, 103700. [CrossRef]
5. Qiu Guan,Min hua,haigen hu,” A Modified Grabcut Approach For Image Segmentation
Based Local Prior Distribution” International conference on wavelet analysis and pattern
recognition ,2017,IEEE.
6. Achanta, R.; Hemami, S.; Estrada, F.; Susstrunk, S. Frequency-tuned salient region
detection. In Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern
Recognition, Miami, FL, USA, 20–25 June 2009; pp. 1597–1604. [Google Scholar]
7. Cheng, M.M.; Mitra, N.J.; Huang, X.; Torr, P.H.S.; Hu, S.-M. Global contrast based salient
region detection. IEEE Trans. Pattern Anal. Mach. Intell. 2014, 37, 569–582. [Google
Scholar] [CrossRef] [PubMed]
8. L. G. de, R. Deriche and C. Alberola-L, "Texture and color segmentation based on the
combined use of the
9. structure tensor and the image components", Signal Processing, vol.88, pp. 776-795, 2008.
10. G. Gerig, O. Kubler, R. Kikinis and F. A. Jolesz, "Nonlinear anisotropic filtering of MRI
data", IEEE
11. Transactions on Medical Imaging, vol.11, pp. 221-232, 1992.
