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.
| Mualliflar | Ахунджанов, Умиджон, Qaxramonov, Sayidumar |
|---|---|
| Jurnal | Al-Farg'oniy avlodlari |
| Nashr sanasi | 2026-06-10 |
| Son | 2 |
| Betlar | 378-383 |
| Til | Rus |
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.
The rapid development of digital technologies in the medical education system is expanding the possibilities of individualizing and increasing the usefulness of educational processes. The purpose of this study is to…
An adaptive area contrast enhancement algorithm is proposed to solve the problem of low contrast in agricultural images. The algorithm automatically detects low contrast regions using local standard deviation and Sobel…
This article provides a scientific and technical overview of the emerging cyber threats to information systems used in the healthcare sector, as well as the functional capabilities of artificial intelligence…
This paper proposes a neuro-fuzzy model based on Sugeno-type ANFIS for adaptive control of urban intersections. The model accounts for the state of not only the central intersection but also four adjacent intersections…
The paper presents a systematic study of stochastic mathematical models and simulation methods applied to evaluating the performance of computing machines. Three queuing models have been formalized and verified — M/M/1…
This article evaluates noise removal and restoration errors using digital processing of ECG signals using wavelet types. As a result of the study, ECG signals were analyzed using second-order Daubechies wavelets, and…
This paper investigates the mathematical framework for managing VM migration in cloud environments. Pre-copy, post-copy and hybrid approaches are formalized, an automatic migration model is developed using a MDP. The…
Note: This article analyzes the process of formation of aphthous lesions in the oral cavity based on mathematical modeling. The aphthous process is a complex biological phenomenon occurring in the oral mucosa, in which…
This article uses the finite difference method to study the stress-strain state of a rectangular plate with a central horizontal crack under plane stress conditions. An equivalent isotropic linear elastic model of…
This article analyzes the use of steganography and digital watermarking (DW) methods in protecting copyright and intellectual property of digital multimedia data. General schemes for placing and extracting digital…