A Signature Recognition Technique With a Powerful Verification Mechanism Based on CNN and PCA
In this paper, we embed a signature verification mechanism in a previously introduced architecture for signature recognition to detect in-distribution and out-of-distribution random forgeries. In the previous architecture, a CNN was trained on the genuine user training dataset and then used as a fea...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10472494/ |
| _version_ | 1797243305400991744 |
|---|---|
| author | Gibrael Abosamra Hadi Oqaibi |
| author_facet | Gibrael Abosamra Hadi Oqaibi |
| author_sort | Gibrael Abosamra |
| collection | DOAJ |
| description | In this paper, we embed a signature verification mechanism in a previously introduced architecture for signature recognition to detect in-distribution and out-of-distribution random forgeries. In the previous architecture, a CNN was trained on the genuine user training dataset and then used as a feature extraction module. A k-NN algorithm with cosine distance was then used to classify the unknown signatures based on the nearest cosine distance neighbor. This architecture led to higher than 99% accuracy, but without verification, because any unknown signature will converge to one of the identities of the training dataset’s users. To add a verification mechanism that differentiates between genuine and random forgeries, we use PCA to select the most discriminating features used in calculating the cosine distance between the training and testing signatures. A fixed parameter thresholding technique based on the training distances is introduced that best differentiates between the genuine and random-user signatures. Moreover, enhancement of the technique is carried out by combining the output of the Softmax layer and the last convolution layer of the ResNet18 model to get a highly discriminative representation of the handwritten signatures. Accordingly, the introduced verification mechanism resulted in very low false positive and negative rates for test signatures from inside and outside the main dataset, with an insignificant decrease in the high identification accuracy. The complete architecture has been tested on three publicly available datasets, showing superior results. |
| first_indexed | 2024-04-24T18:53:00Z |
| format | Article |
| id | doaj.art-95b93d3335ea46d78140913d4560c5d4 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-24T18:53:00Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-95b93d3335ea46d78140913d4560c5d42024-03-26T17:48:09ZengIEEEIEEE Access2169-35362024-01-0112406344065610.1109/ACCESS.2024.337745510472494A Signature Recognition Technique With a Powerful Verification Mechanism Based on CNN and PCAGibrael Abosamra0https://orcid.org/0000-0003-4871-1867Hadi Oqaibi1https://orcid.org/0000-0003-3990-2688Department of Computer Information Systems, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah, Saudi ArabiaDepartment of Computer Information Systems, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah, Saudi ArabiaIn this paper, we embed a signature verification mechanism in a previously introduced architecture for signature recognition to detect in-distribution and out-of-distribution random forgeries. In the previous architecture, a CNN was trained on the genuine user training dataset and then used as a feature extraction module. A k-NN algorithm with cosine distance was then used to classify the unknown signatures based on the nearest cosine distance neighbor. This architecture led to higher than 99% accuracy, but without verification, because any unknown signature will converge to one of the identities of the training dataset’s users. To add a verification mechanism that differentiates between genuine and random forgeries, we use PCA to select the most discriminating features used in calculating the cosine distance between the training and testing signatures. A fixed parameter thresholding technique based on the training distances is introduced that best differentiates between the genuine and random-user signatures. Moreover, enhancement of the technique is carried out by combining the output of the Softmax layer and the last convolution layer of the ResNet18 model to get a highly discriminative representation of the handwritten signatures. Accordingly, the introduced verification mechanism resulted in very low false positive and negative rates for test signatures from inside and outside the main dataset, with an insignificant decrease in the high identification accuracy. The complete architecture has been tested on three publicly available datasets, showing superior results.https://ieeexplore.ieee.org/document/10472494/Convolutional neural networkscosine distancefalse negative ratefalse positive ratek-Nearest neighbor algorithmout-of-distribution detection |
| spellingShingle | Gibrael Abosamra Hadi Oqaibi A Signature Recognition Technique With a Powerful Verification Mechanism Based on CNN and PCA IEEE Access Convolutional neural networks cosine distance false negative rate false positive rate k-Nearest neighbor algorithm out-of-distribution detection |
| title | A Signature Recognition Technique With a Powerful Verification Mechanism Based on CNN and PCA |
| title_full | A Signature Recognition Technique With a Powerful Verification Mechanism Based on CNN and PCA |
| title_fullStr | A Signature Recognition Technique With a Powerful Verification Mechanism Based on CNN and PCA |
| title_full_unstemmed | A Signature Recognition Technique With a Powerful Verification Mechanism Based on CNN and PCA |
| title_short | A Signature Recognition Technique With a Powerful Verification Mechanism Based on CNN and PCA |
| title_sort | signature recognition technique with a powerful verification mechanism based on cnn and pca |
| topic | Convolutional neural networks cosine distance false negative rate false positive rate k-Nearest neighbor algorithm out-of-distribution detection |
| url | https://ieeexplore.ieee.org/document/10472494/ |
| work_keys_str_mv | AT gibraelabosamra asignaturerecognitiontechniquewithapowerfulverificationmechanismbasedoncnnandpca AT hadioqaibi asignaturerecognitiontechniquewithapowerfulverificationmechanismbasedoncnnandpca AT gibraelabosamra signaturerecognitiontechniquewithapowerfulverificationmechanismbasedoncnnandpca AT hadioqaibi signaturerecognitiontechniquewithapowerfulverificationmechanismbasedoncnnandpca |