O‘ZBEK LOTIN ALIFBOSI QO‘L YOZUVI BELGILARINI ANIQLASH TIZIMINING TADQIQOT METODOLOGIYASI VA TAKLIF ETILAYOTGAN GIBRID ALGORITM ARXITEKTURASI
DOI:
https://doi.org/10.65164/m772q751Kalit so‘zlar:
qo‘l yozuvi tanish, gibrid algoritm, CNN, SVM, DFD, Use Case, o‘zbek lotin alifbosi.Abstrak
Ushbu tezisda o‘zbek lotin alifbosi qo‘l yozuvi belgilarini aniqlash uchun taklif etilayotgan gibrid algoritm va tizim arxitekturasi yoritiladi. Tadqiqot metodologiyasi, maqsad va vazifalar, ilmiy gipoteza, funksional model (DFD), foydalanuvchi holatlari (Use Case) va gibrid arxitektura (oldindan ishlov berish + segmentatsiya + CNN + SVM) komponentlari batafsil ko‘rib chiqiladi. Gibrid yondashuv an’anaviy usullarga nisbatan aniqlikni 10–20% ga oshirishi ko‘rsatilgan. Eksperimentlar natijasida 94–96% aniqlikka erishilgan. Tizim raqamli arxivlar, ta’lim va hujjatlar raqamlashtirishda qo‘llash uchun mos
Havolalar
[1] Ahlawat, S., & Choudhary, A. (2020). Hybrid CNN-SVM classifier for handwritten digit
recognition. Procedia Computer Science, 167, 2554-2560.
[2] Mardiev A., Allayorov J., Alisherova S. (2025). Methods and Algorithms for Detecting Text
Regions in Handwritten Document Images Computer Science and Information Technology 13(3):
49-56,
[3] Niu, X. X., & Suen, C. Y. (2012). A novel hybrid CNN–SVM classifier for recognizing
handwritten digits. Pattern recognition, 45(4), 1318-1325.
[4] Iskandarova, S., & Kuchkarov, Z. (2023). RECOGNITION OF UZBEK HANDWRITTEN
TEXTS BY SELECTION OF ACTIVATION FUNCTIONS FOR CONVOLUTIONAL
NEURAL NETWORK. Science and innovation, 2(A2), 16-21.
