On the Use of Edge Features and Exponential Decaying Number of Nodes in the Hidden Layers for Handwritten Signature Recognition
| Main Authors: | Teddy Surya Gunawan, Mira Kartiwi |
|---|---|
| Format: | Article Journal |
| Terbitan: |
, 2018
|
| Subjects: | |
| Online Access: |
https://zenodo.org/record/4314539 |
| ctrlnum |
4314539 |
|---|---|
| fullrecord |
<?xml version="1.0"?>
<dc schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd"><creator>Teddy Surya Gunawan</creator><creator>Mira Kartiwi</creator><date>2018-11-01</date><description>Handwritten signatures are playing an important role in finance, banking and education and more because it is considered the “seal of approval” and remains the most preferred means of authentication. In this paper, an offline handwritten signature authentication algorithm is proposed using the edge features and deep feedforward neural network (DFNN). The number of hidden layers in DFNN is configured to be at least one layer and more. In this paper, an exponential decaying number of nodes in the hidden layers was proposed to achieve better recognition rate with reasonable training time. Of the six edge algorithms evaluated, Roberts operator and Canny edge detectors were found to produce better recognition rate. Results showed that the proposed exponential decaying number of nodes in the hidden layers outperform other structure. However, more training data was required so that the proposed DFNN structure could have more efficient learning.</description><identifier>https://zenodo.org/record/4314539</identifier><identifier>10.11591/ijeecs.v12.i2.pp722-728</identifier><identifier>oai:zenodo.org:4314539</identifier><rights>info:eu-repo/semantics/openAccess</rights><rights>https://creativecommons.org/licenses/by/4.0/legalcode</rights><source>Indonesian Journal of Electrical Engineering and Computer Science 12(2) 722-728</source><subject>Deep feedforward neural network</subject><subject>Edge detection</subject><subject>Exponential decaying</subject><subject>Hidden layers</subject><subject>Offline handwritten signature</subject><title>On the Use of Edge Features and Exponential Decaying Number of Nodes in the Hidden Layers for Handwritten Signature Recognition</title><type>Journal:Article</type><type>Journal:Article</type><recordID>4314539</recordID></dc>
|
| format |
Journal:Article Journal Journal:Journal |
| author |
Teddy Surya Gunawan Mira Kartiwi |
| title |
On the Use of Edge Features and Exponential Decaying Number of Nodes in the Hidden Layers for Handwritten Signature Recognition |
| publishDate |
2018 |
| topic |
Deep feedforward neural network Edge detection Exponential decaying Hidden layers Offline handwritten signature |
| url |
https://zenodo.org/record/4314539 |
| contents |
Handwritten signatures are playing an important role in finance, banking and education and more because it is considered the “seal of approval” and remains the most preferred means of authentication. In this paper, an offline handwritten signature authentication algorithm is proposed using the edge features and deep feedforward neural network (DFNN). The number of hidden layers in DFNN is configured to be at least one layer and more. In this paper, an exponential decaying number of nodes in the hidden layers was proposed to achieve better recognition rate with reasonable training time. Of the six edge algorithms evaluated, Roberts operator and Canny edge detectors were found to produce better recognition rate. Results showed that the proposed exponential decaying number of nodes in the hidden layers outperform other structure. However, more training data was required so that the proposed DFNN structure could have more efficient learning. |
| id |
IOS16997.4314539 |
| institution |
ZAIN Publications |
| institution_id |
7213 |
| institution_type |
library:special library |
| library |
Cognizance Journal of Multidisciplinary Studies |
| library_id |
5267 |
| collection |
Cognizance Journal of Multidisciplinary Studies |
| repository_id |
16997 |
| subject_area |
Multidisciplinary |
| city |
Stockholm |
| province |
INTERNASIONAL |
| shared_to_ipusnas_str |
1 |
| repoId |
IOS16997 |
| first_indexed |
2022-06-06T04:56:34Z |
| last_indexed |
2022-06-06T04:56:34Z |
| recordtype |
dc |
| _version_ |
1734903706012352512 |
| score |
17.538404 |