Online Persian/Arabic Writer Identification using Gated Recurrent Unit Neural Networks
Conventional methods in writer identification mostly rely on hand-crafted features to represent the characteristics of different handwritten scripts. In this paper, we propose an end-to-end model for online text-independent writer identification on Persian/Arabic online handwritten scripts by using...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
OICC Press
2024-02-01
|
| Series: | Majlesi Journal of Electrical Engineering |
| Subjects: | |
| Online Access: | https://oiccpress.com/mjee/article/view/4884 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849415844980850688 |
|---|---|
| author | Mahsa Aliakbarzadeh Farbod Razzazi |
| author_facet | Mahsa Aliakbarzadeh Farbod Razzazi |
| author_sort | Mahsa Aliakbarzadeh |
| collection | DOAJ |
| description | Conventional methods in writer identification mostly rely on hand-crafted features to represent the characteristics of different handwritten scripts. In this paper, we propose an end-to-end model for online text-independent writer identification on Persian/Arabic online handwritten scripts by using Gated Recurrent Unit (GRU) neural networks. The method does not require any specific knowledge for handwriting data analysis. Because of the exclusive ability of deep neural networks, we just represented our data by Random Strokes (RS) representations, which are differential horizontal and vertical coordinates extracted from different handwritings with a predefined length. This representation is a context independent representation. Therefore, this writer identification at RS level is more general than character level or word level in identification systems, which require character or word segmentation. The RS representation is then fed to a GRU neural network to represent the sequence for final classification. All RS features of a writer are then classified independently, and in the final stage, the posterior probabilities are averaged to make the final decision. Experiments on KHATT database, which consists of online handwritings of Arabic writers, gave us 100% accuracy on 10 writers and 76% accuracy on 50 writers, which is much better than previous works on online Persian/Arabic writer identification. |
| format | Article |
| id | doaj-art-ba13fae2601e40769f281c42ababe92a |
| institution | Kabale University |
| issn | 2345-377X 2345-3796 |
| language | English |
| publishDate | 2024-02-01 |
| publisher | OICC Press |
| record_format | Article |
| series | Majlesi Journal of Electrical Engineering |
| spelling | doaj-art-ba13fae2601e40769f281c42ababe92a2025-08-20T03:33:22ZengOICC PressMajlesi Journal of Electrical Engineering2345-377X2345-37962024-02-0114310.29252/mjee.14.3.9Online Persian/Arabic Writer Identification using Gated Recurrent Unit Neural NetworksMahsa AliakbarzadehFarbod RazzaziConventional methods in writer identification mostly rely on hand-crafted features to represent the characteristics of different handwritten scripts. In this paper, we propose an end-to-end model for online text-independent writer identification on Persian/Arabic online handwritten scripts by using Gated Recurrent Unit (GRU) neural networks. The method does not require any specific knowledge for handwriting data analysis. Because of the exclusive ability of deep neural networks, we just represented our data by Random Strokes (RS) representations, which are differential horizontal and vertical coordinates extracted from different handwritings with a predefined length. This representation is a context independent representation. Therefore, this writer identification at RS level is more general than character level or word level in identification systems, which require character or word segmentation. The RS representation is then fed to a GRU neural network to represent the sequence for final classification. All RS features of a writer are then classified independently, and in the final stage, the posterior probabilities are averaged to make the final decision. Experiments on KHATT database, which consists of online handwritings of Arabic writers, gave us 100% accuracy on 10 writers and 76% accuracy on 50 writers, which is much better than previous works on online Persian/Arabic writer identification.https://oiccpress.com/mjee/article/view/4884End-to-End IdentificationGRUHandcrafted FeaturesOnline Writer Identification |
| spellingShingle | Mahsa Aliakbarzadeh Farbod Razzazi Online Persian/Arabic Writer Identification using Gated Recurrent Unit Neural Networks Majlesi Journal of Electrical Engineering End-to-End Identification GRU Handcrafted Features Online Writer Identification |
| title | Online Persian/Arabic Writer Identification using Gated Recurrent Unit Neural Networks |
| title_full | Online Persian/Arabic Writer Identification using Gated Recurrent Unit Neural Networks |
| title_fullStr | Online Persian/Arabic Writer Identification using Gated Recurrent Unit Neural Networks |
| title_full_unstemmed | Online Persian/Arabic Writer Identification using Gated Recurrent Unit Neural Networks |
| title_short | Online Persian/Arabic Writer Identification using Gated Recurrent Unit Neural Networks |
| title_sort | online persian arabic writer identification using gated recurrent unit neural networks |
| topic | End-to-End Identification GRU Handcrafted Features Online Writer Identification |
| url | https://oiccpress.com/mjee/article/view/4884 |
| work_keys_str_mv | AT mahsaaliakbarzadeh onlinepersianarabicwriteridentificationusinggatedrecurrentunitneuralnetworks AT farbodrazzazi onlinepersianarabicwriteridentificationusinggatedrecurrentunitneuralnetworks |