Vol. 3 No. 05 (2026): INTERNATIONAL JOURNAL OF SCIENCE AND TECHNOLOGY
Articles

BELGILARNI ANIQLASH VA AJRATIB OLISHNING NAZARIY ASOSLARI VA ALGORITMIK YONDASHUVLARI

PDF
  • Roxmonova Ma’rifat Shuxrat qizi
Roxmonova Ma’rifat Shuxrat qizi
Magistratura talabasi, Abu Rayhon Beruniy nomidagi Urganch davlat universiteti

Published 19-06-2026

Keywords

  • qo‘l yozuvi tanish, OCR, segmentatsiya, CRNN, attention, transformer, kompyuter ko‘rish.
Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

BELGILARNI ANIQLASH VA AJRATIB OLISHNING NAZARIY ASOSLARI VA ALGORITMIK YONDASHUVLARI. (2026). INTERNATIONAL JOURNAL OF SCIENCE AND TECHNOLOGY, 3(05), 24-29. https://doi.org/10.70728/tech.v3.i05.006

Abstract

Qo‘l yozuvi matnlarini avtomatik aniqlash va tanib olish masalasi kompyuter ko‘rish hamda sun’iy intellekt sohalarining eng murakkab yo‘nalishlaridan biri hisoblanadi. Ushbu ishda belgilarni aniqlash va ajratib olish jarayonining nazariy asoslari hamda zamonaviy algoritmik yondashuvlari ilmiy adabiyotlar asosida tahlil qilinadi. Tadqiqotlar shuni ko‘rsatadiki, qo‘l yozuvi tanish tizimlarida segmentatsiya bosqichi eng muhim va murakkab jarayonlardan biri bo‘lib, uning xatolari butun OCR tizimi aniqligiga sezilarli ta’sir ko‘rsatadi. Zamonaviy ishlarda segmentatsiyaga asoslangan, segmentatsiyasiz va gibrid yondashuvlar qo‘llanilmoqda. Chuqur o‘rganishga asoslangan konvolyutsion, rekurrent va attention mexanizmlaridan foydalanadigan modellar qo‘l yozuvini tanishda yuqori samaradorlik ko‘rsatmoqda. Ushbu tezisda mavjud ilmiy ishlardagi metodlar umumlashtirilib, belgilarni aniqlash tizimlarini yaratishda ularning nazariy ahamiyati asoslab beriladi.

PDF

References

  1. [1] Coquenet, D., Chatelain, C., & Paquet, T. (2023). Dan: a segmentation-free document attention network for handwritten document recognition. IEEE transactions on pattern analysis and machine intelligence, 45(7), 8227-8243.
  2. [2] Tensmeyer, C., & Wigington, C. (2019, September). Training full-page handwritten text recognition models without annotated line breaks. In 2019 International conference on document analysis and recognition (ICDAR) (pp. 1-8). IEEE.
  3. [3] Minz, S., Kanojia, R., Yadav, T., & Jayanthi, N. (2023, May). Enhancing accuracy in handwritten text recognition with convolutional recurrent neural network and data augmentation techniques. In 2023 Third International Conference on Secure Cyber Computing and Communication (ICSCCC) (pp. 803-808). IEEE..
  4. [4] Nguyen, C. T., & Nakagawa, M. (2015, November). An improved segmentation of online English handwritten text using recurrent neural networks. In 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR) (pp. 176-180). IEEE.
  5. [5] Nguyen, K. C., Nguyen, C. T., & Nakagawa, M. (2020, September). A semantic segmentation-based method for handwritten Japanese text recognition. In 2020 17th International Conference on Frontiers in Handwriting Recognition (ICFHR) (pp. 127-132). IEEE.
  6. [6] Varpe, K., Sakhare, S., & Joshi, R. (2025, January). Enhancing Accuracy of Handwritten Character Segmentation Using Region-Based Convolutional Neural Networks (R-CNN). In 2025 1st International Conference on AIML-Applications for Engineering & Technology (ICAET) (pp. 1-6). IEEE.
  7. [7] Li, D., Wu, Y., & Zhou, Y. (2021, September). Linecounter: learning handwritten text line segmentation by counting. In 2021 IEEE International Conference on Image Processing (ICIP) (pp. 929-933). IEEE.
  8. [8] Coquenet, D., Chatelain, C., & Paquet, T. (2022). End-to-end handwritten paragraph text recognition using a vertical attention network. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(1), 508-524