METHODS AND ALGORITHMS FOR IMPROVING OFFLINE SIGNATURE VERIFICATION SYSTEMS BASED ON CNN AND OCSVM

Ахунджанов, Умиджон, Qaxramonov, Sayidumar

Al-Farg'oniy avlodlari · 2026-yil

Annotatsiya

This article investigates the issues of improving the verification accuracy by improving the quality of digital signature images in offline signature verification systems. During the study, the impact of factors such as noise, low contrast, and image deformations in signature images on the verification process was analyzed. The quality of signature images was improved by using image preprocessing, filtering, binarization, and morphological processing algorithms. The effectiveness of median and Gaussian filters was evaluated based on the CEDAR Signature Dataset and BHSig260 databases. CNN and One-Class Support Vector Machine (OCSVM) algorithms were used at the verification stage.

Maqola ma’lumotlari
MualliflarАхунджанов, Умиджон, Qaxramonov, Sayidumar
JurnalAl-Farg'oniy avlodlari
Nashr sanasi2026-06-10
Son2
Betlar378-383
TilRus

Kalit so‘zlar

biometrik identifikatsiya, oflayn imzo verifikatsiyasi, CNN, OCSVM, tasvirlarga ishlov berish, median filter, gaussian filter, binarlashtirish, morfologik amallar, tasvir sifatini oshirish, biometric identification, offline signature verification, CNN, OCSVM, image processing, median filter, gaussian filter, binarization, morphological operations, image quality enhancement.

Ilmiy soha

Al-Farg'oniy avlodlari jurnalidan boshqa maqolalar

Al-Farg'oniy avlodlari — barcha maqolalar