INTERPOLATSION TIKLASH ALGORITMLARINING OCR ANIQLIGIGA TA’SIRINI BAHOLASH

Aliyev N. H.


Annotatsiya

Ushbu maqolada tasvirlarni dinamik rekonstruksiya qilish va OCR tizimlarining samaradorligini oshirishda qo‘llaniladigan adaptiv interpolatsion tiklash algoritmlarining hisoblash murakkabligi va resurs samaradorligi tadqiq etiladi. Tadqiqot doirasida an'anaviy bilinear va bikubik interpolatsiya usullarining asimptotik murakkabligi hamda ularning lokal gradyent o‘zgarishlariga moslashuvchan (adaptiv) algoritmlar bilan qiyosiy tahlili keltirilgan. Algoritmlarning hisoblash murakkabligi O-notatsiya asosida baholanib, vaqt va xotira resurslariga bo‘lgan talablari matematik modellar orqali asoslanadi. Shuningdek, tasvir chetlarini saqlab qolish va artefaktlarni kamaytirishda adaptiv yondashuvlarning iqtisodiy-texnik samaradorligi, ayniqsa yuqori aniqlikdagi tasvirlarni real vaqt rejimida qayta ishlash tizimlaridagi o‘rni tahlil qilingan. Tadqiqot natijalari hisoblash quvvatini optimallashtirish va algoritmlarning amaliy samaradorligini oshirish bo‘yicha ilmiy tavsiyalar berishga xizmat qiladi.


Adabiyotlar

  1. UNCTAD. Digital Economy Report 2024: Shaping the Future of Data-Driven Development. United Nations, 2024.
  2. Grand View Research. Image Processing Market Size, Share & Trends Analysis Report, 2023–2030.
  3. Statista. Global Cloud Computing Market Costs and Resource Allocation Statistics, 2025.
  4. O‘zbekiston Respublikasi Raqamli texnologiyalar vazirligi. Raqamli transformatsiya jarayonlari bo‘yicha yillik hisobot, 2025.
  5. IEEE Xplore. Efficiency Analysis of Adaptive Interpolation Methods in Real-Time Image Processing Systems. IEEE Transactions on Image Processing, 2024.
  6. Gonzalez R.C., Woods R.E. Digital Image Processing. 4th Edition. New York: Pearson Education, 2018. 1168 p.
  7. Pratt W.K. Digital Image Processing: PIKS Scientific Interior. 4th Edition. New Jersey: Wiley-Interscience, 2007. 807 p.
  8. Forsyth D.A., Ponce J. Computer Vision: A Modern Approach. 2nd Edition. New Jersey: Pearson, 2011. 792 p.
  9. Smith R. An Overview of the Tesseract OCR Engine. Proceedings of the Ninth International Conference on Document Analysis and Recognition (ICDAR 2007). IEEE Computer Society, 2007. pp. 629–633.
  10. Shafait M., Keysers D., Breuel T.M. Efficient Implementation of Local Adaptive Thresholding Techniques Using Integral Images. Document Analysis Systems. Springer, 2008. pp. 339–346.
  11. Gatos B., Pratikakis I., Perantonis S.J. Adaptive Degraded Document Image Binarization. Pattern Recognition. Elsevier, 2006. Vol. 39, Issue 3. pp. 317–327.
  12. Otsu N. A Threshold Selection Method from Gray-Level Histograms. IEEE Transactions on Systems, Man, and Cybernetics, 1979. Vol. 9, Issue 1. pp. 62–66.
  13. Sodiqov S.S., Malikov M.N. Tasvirlarga raqamli ishlov berish asoslari. Toshkent: Innovatsion rivojlanish nashriyot-matbaa uyi, 2021. 256 b.
  14. Tuxtasinov M.T. Tasvirlarni dastlabki qayta ishlash va strukturaviy tahlil algoritmlari. Namangan: Fan va texnologiya, 2022. 184 b.
  15. Samandarov I.R. Tasvirlardan informativ belgilarni ajratish va tanib olish tizimlari. Toshkent: O‘zbekiston milliy ensiklopediyasi, 2023. 210 b.