Verification of a static (off-line) signature using a convolutional neural network
This article is devoted to the development of a method for detecting forgery of handwritten signatures. The signature still remains one of the most common methods of identification. The signature on financial and other documents can be forged, so detecting forgery is an urgent task. This is the task...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Belarusian National Technical University
2022-06-01
|
| Series: | Системный анализ и прикладная информатика |
| Subjects: | |
| Online Access: | https://sapi.bntu.by/jour/article/view/547 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832543642421559296 |
|---|---|
| author | U. Yu. Akhundjanov V. V. Starovoitov |
| author_facet | U. Yu. Akhundjanov V. V. Starovoitov |
| author_sort | U. Yu. Akhundjanov |
| collection | DOAJ |
| description | This article is devoted to the development of a method for detecting forgery of handwritten signatures. The signature still remains one of the most common methods of identification. The signature on financial and other documents can be forged, so detecting forgery is an urgent task. This is the task of binary classification: to determine whether the signature is genuine or fake.The article describes the results of recognition of handwritten signatures made on paper. A database of handwritten signatures of 10 people was used for experiments. For each person, 10 genuine and 10 forgery signatures made by other people were collected. The signatures were digitized as color images with a resolution of 850×550 pixels. Then a binary representation of each signature was formed. Three variants of reducing signatures to sizes were used for classification: 128×128, 256×256 and 512×512 pixels. These images served as the source data for the convolutional neural network.As a result of testing the proposed approach, the average accuracy of the correct classification was achieved on medium-sized images and is equal to 93.33%. |
| format | Article |
| id | doaj-art-70403c08b41d48c4af693916d81454b6 |
| institution | Kabale University |
| issn | 2309-4923 2414-0481 |
| language | English |
| publishDate | 2022-06-01 |
| publisher | Belarusian National Technical University |
| record_format | Article |
| series | Системный анализ и прикладная информатика |
| spelling | doaj-art-70403c08b41d48c4af693916d81454b62025-02-03T11:37:40ZengBelarusian National Technical UniversityСистемный анализ и прикладная информатика2309-49232414-04812022-06-0101121810.21122/2309-4923-2022-1-12-18409Verification of a static (off-line) signature using a convolutional neural networkU. Yu. Akhundjanov0V. V. Starovoitov1United Institute of Informatics Problems, National Academy of Sciences of BelarusUnited Institute of Informatics Problems, National Academy of Sciences of BelarusThis article is devoted to the development of a method for detecting forgery of handwritten signatures. The signature still remains one of the most common methods of identification. The signature on financial and other documents can be forged, so detecting forgery is an urgent task. This is the task of binary classification: to determine whether the signature is genuine or fake.The article describes the results of recognition of handwritten signatures made on paper. A database of handwritten signatures of 10 people was used for experiments. For each person, 10 genuine and 10 forgery signatures made by other people were collected. The signatures were digitized as color images with a resolution of 850×550 pixels. Then a binary representation of each signature was formed. Three variants of reducing signatures to sizes were used for classification: 128×128, 256×256 and 512×512 pixels. These images served as the source data for the convolutional neural network.As a result of testing the proposed approach, the average accuracy of the correct classification was achieved on medium-sized images and is equal to 93.33%.https://sapi.bntu.by/jour/article/view/547recognitionverificationhandwritten signatureclassificationfrrfar |
| spellingShingle | U. Yu. Akhundjanov V. V. Starovoitov Verification of a static (off-line) signature using a convolutional neural network Системный анализ и прикладная информатика recognition verification handwritten signature classification frr far |
| title | Verification of a static (off-line) signature using a convolutional neural network |
| title_full | Verification of a static (off-line) signature using a convolutional neural network |
| title_fullStr | Verification of a static (off-line) signature using a convolutional neural network |
| title_full_unstemmed | Verification of a static (off-line) signature using a convolutional neural network |
| title_short | Verification of a static (off-line) signature using a convolutional neural network |
| title_sort | verification of a static off line signature using a convolutional neural network |
| topic | recognition verification handwritten signature classification frr far |
| url | https://sapi.bntu.by/jour/article/view/547 |
| work_keys_str_mv | AT uyuakhundjanov verificationofastaticofflinesignatureusingaconvolutionalneuralnetwork AT vvstarovoitov verificationofastaticofflinesignatureusingaconvolutionalneuralnetwork |