A Novel Technique for Handwritten Signature Recognition
Handwritten signature recognition (HSR) is a critical component of biometric systems, widely used for securing financial transactions and identity verification. However, the variability of handwritten signatures, influenced by individual writing styles, inconsistencies, and environmental factors, p...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Universidade Federal de Viçosa (UFV)
2024-12-01
|
| Series: | The Journal of Engineering and Exact Sciences |
| Subjects: | |
| Online Access: | https://periodicos.ufv.br/jcec/article/view/20810 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832569824854671360 |
|---|---|
| author | Leila Boucerredj Karima Kechroud Bouaziz Noureddine Abderrahmane Khechekhouche |
| author_facet | Leila Boucerredj Karima Kechroud Bouaziz Noureddine Abderrahmane Khechekhouche |
| author_sort | Leila Boucerredj |
| collection | DOAJ |
| description |
Handwritten signature recognition (HSR) is a critical component of biometric systems, widely used for securing financial transactions and identity verification. However, the variability of handwritten signatures, influenced by individual writing styles, inconsistencies, and environmental factors, presents significant challenges for recognition systems. Despite these obstacles, signatures remain a reliable and popular biometric trait. This paper introduces a novel deep learning approach utilizing a convolutional neural network (CNN) architecture specifically designed for HSR. The proposed method was validated using two prominent datasets, MCYT-75 and GPDS-300, with detailed descriptions of the CNN structure. Experiments, conducted on a personal computer equipped with an NVIDIA Quadro M1200 GPU, an Intel i7 processor, and 32 GB of RAM, demonstrated the model’s exceptional performance, achieving validation accuracies of 99.60% on the MCYT-75 dataset and 99.80% on the GPDS-300 dataset. These results reflect the model’s robustness and minimized error rates, outperforming existing techniques and underscoring the effectiveness of deep learning for signature recognition. This study highlights the proposed model's potential for real-world applications and paves the way for further advancements in biometric authentication technologies.
|
| format | Article |
| id | doaj-art-ba863340a0d54731a0176d2662709a29 |
| institution | Kabale University |
| issn | 2527-1075 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Universidade Federal de Viçosa (UFV) |
| record_format | Article |
| series | The Journal of Engineering and Exact Sciences |
| spelling | doaj-art-ba863340a0d54731a0176d2662709a292025-02-02T19:53:10ZengUniversidade Federal de Viçosa (UFV)The Journal of Engineering and Exact Sciences2527-10752024-12-0110810.18540/jcecvl10iss8pp20810A Novel Technique for Handwritten Signature RecognitionLeila Boucerredj0Karima Kechroud1Bouaziz Noureddine2Abderrahmane Khechekhouche3Department of Electronics and Automatics, Faculty of Science and Technology, PIMIS, Laboratory, University of 8 Mai 1945, PO Box 401, GUELMA 24000, AlgeriaDepartment of Electronics and Automatics, Faculty of Science and Technology, PIMIS, Laboratory, University of 8 Mai 1945, PO Box 401, GUELMA 24000, AlgeriaDepartment of Electronics and Automatics, Faculty of Science and Technology, PIMIS, Laboratory, University of 8 Mai 1945, PO Box 401, GUELMA 24000, AlgeriaLaboratory (LNTDL), Faculty of Technology, University of El Oued, Algeria Handwritten signature recognition (HSR) is a critical component of biometric systems, widely used for securing financial transactions and identity verification. However, the variability of handwritten signatures, influenced by individual writing styles, inconsistencies, and environmental factors, presents significant challenges for recognition systems. Despite these obstacles, signatures remain a reliable and popular biometric trait. This paper introduces a novel deep learning approach utilizing a convolutional neural network (CNN) architecture specifically designed for HSR. The proposed method was validated using two prominent datasets, MCYT-75 and GPDS-300, with detailed descriptions of the CNN structure. Experiments, conducted on a personal computer equipped with an NVIDIA Quadro M1200 GPU, an Intel i7 processor, and 32 GB of RAM, demonstrated the model’s exceptional performance, achieving validation accuracies of 99.60% on the MCYT-75 dataset and 99.80% on the GPDS-300 dataset. These results reflect the model’s robustness and minimized error rates, outperforming existing techniques and underscoring the effectiveness of deep learning for signature recognition. This study highlights the proposed model's potential for real-world applications and paves the way for further advancements in biometric authentication technologies. https://periodicos.ufv.br/jcec/article/view/20810Biometric Recognition, Deep Learning (DL), Handwritten Signatures, CNN, MCYT-75 and GPDS-300 database. |
| spellingShingle | Leila Boucerredj Karima Kechroud Bouaziz Noureddine Abderrahmane Khechekhouche A Novel Technique for Handwritten Signature Recognition The Journal of Engineering and Exact Sciences Biometric Recognition, Deep Learning (DL), Handwritten Signatures, CNN, MCYT-75 and GPDS-300 database. |
| title | A Novel Technique for Handwritten Signature Recognition |
| title_full | A Novel Technique for Handwritten Signature Recognition |
| title_fullStr | A Novel Technique for Handwritten Signature Recognition |
| title_full_unstemmed | A Novel Technique for Handwritten Signature Recognition |
| title_short | A Novel Technique for Handwritten Signature Recognition |
| title_sort | novel technique for handwritten signature recognition |
| topic | Biometric Recognition, Deep Learning (DL), Handwritten Signatures, CNN, MCYT-75 and GPDS-300 database. |
| url | https://periodicos.ufv.br/jcec/article/view/20810 |
| work_keys_str_mv | AT leilaboucerredj anoveltechniqueforhandwrittensignaturerecognition AT karimakechroud anoveltechniqueforhandwrittensignaturerecognition AT bouaziznoureddine anoveltechniqueforhandwrittensignaturerecognition AT abderrahmanekhechekhouche anoveltechniqueforhandwrittensignaturerecognition AT leilaboucerredj noveltechniqueforhandwrittensignaturerecognition AT karimakechroud noveltechniqueforhandwrittensignaturerecognition AT bouaziznoureddine noveltechniqueforhandwrittensignaturerecognition AT abderrahmanekhechekhouche noveltechniqueforhandwrittensignaturerecognition |