IMZONI TANIB OLISHDA QO‘LLANILADIGAN ASOSIY ALGORITMLAR: KLASSIK VA ZAMONAVIY METODLARNING SOLISHTIRILGAN TAHLILI
Keywords:
imzoni tanib olish, klassik algoritmlar, zamonaviy algoritmlar, CNN, DTW, SVM, LSTM, biometrik autentifikatsiya, algoritmik tahlil, aniqlik.Abstract
Tadqiqotda imzoni avtomatik tanib olish jarayonida qo‘llaniladigan algoritmlarning turlari va ularning samaradorlik darajasi tahlil qilinadi. Klassik yondashuvlar — Template Matching, Euclidean Distance, Dynamic Time Warping (DTW) — va zamonaviy metodlar — Support Vector Machine (SVM), Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM) — funksional va texnologik mezonlar asosida solishtirildi. Tadqiqot natijalari klassik metodlar oddiy strukturali tizimlarda samarali bo‘lsa-da, zamonaviy chuqur o‘rganish modellarining aniqlik darajasi, barqarorlik va moslashuvchanlikda ustunligini ko‘rsatdi.
References
Plamondon, R., & Lorette, G. (1989). Automatic Signature Verification and Writer Identification – The State of the Art. Pattern Recognition, 22(2), 107–131.
Jain, A. K., Ross, A., & Nandakumar, K. (2011). Introduction to Biometrics. Springer.
Maltoni, D., Maio, D., Jain, A. K., & Prabhakar, S. (2009). Handbook of Biometrics. Springer Science & Business Media.
Said, E., Georgiou, T., & Ferrer, M. A. (2019). Offline Signature Verification Using CNNs and Deep Learning Techniques. IET Biometrics, 8(2), 134–142.
Hafemann, L. G., Oliveira, L. S., & Sabourin, R. (2017). Offline handwritten signature verification—literature review. Pattern Recognition, 70, 270–291.
