cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Jares
Contact Email
ejournal@unisbablitar.ac.id
Phone
-
Journal Mail Official
jaresunisbablitar@gmail.com
Editorial Address
Jalan Majapahit No. 4, Kec. Sananwetan, Kota Blitar
Location
Kota blitar,
Jawa timur
INDONESIA
JARES (Journal of Academic Research and Sciences)
Published by Universitas Islam Balitar Blitar
ISSN : 2502826X     EISSN : 25031163     DOI : https://doi.org/10.35457/jares
Core Subject : Social,
Social Sciences
Jurnal memuat hasil penelitian di perguruan tinggi bidang ilmu sosial, humaniora dan sains.
Arjuna Subject : -
Articles 1 Documents
 1 
Search results for , issue "Vol 10 No 2 (2025): September 2025" : 1 Documents clear
A Convolutional Neural Network Model for the Handwritten Hijaiyah Recognition System (SiPuTiH) with Domain-Specific Data Augmentation Sri Lestanti; Sandi Widya Permana; Nur Budiman, Saiful
JARES (Journal of Academic Research and Sciences) Vol 10 No 2 (2025): September 2025
Publisher : Universitas Islam Balitar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35457/jares.v10i2.5430

Abstract

This paper presents SiPuTiH, a Convolutional Neural Network (CNN)-based approach for handwritten Hijaiyah character recognition that addresses performance degradation caused by morphological variations in handwriting. The study employs a dataset of 1,680 handwritten images representing 30 Hijaiyah characters, where domain-specific data augmentation is applied solely during the training phase. The augmentation strategy incorporates controlled geometric and stroke-based transformations, including rotation, scaling, shear, slant variation, and stroke thickness adjustment, to model realistic handwriting diversity. The proposed CNN architecture consists of multiple convolutional layers with ReLU activation, max-pooling operations, and a softmax classifier. Experimental results show that the proposed method achieves an accuracy of 99.70%, with weighted precision and F1-score of 99.85% and 99.77%, respectively. Furthermore, the use of domain-specific data augmentation effectively reduces misclassification among visually similar characters, such as ta and tsa, demonstrating improved robustness and generalization capability.

Page 1 of 1 | Total Record : 1

 1 

Filter by Year

2025 2025


Reset
Filter By Issues
All Issue Vol 10 No 2 (2025): September 2025 Vol 9 No 2 (2024): September 2024 Vol 9 No 1 (2024): March 2024 Vol 8 No 2 (2023): September 2023 Vol 8 No 1 (2023): March 2023 Vol 7 No 2 (2022): September 2022 Vol 7 No 1 (2022): March 2022 Vol 6 No 2 (2021): September 2021 Vol 6 No 1 (2021): March 2021 Vol 5 No 2 (2020): September 2020 Vol 5 No 1 (2020): March 2020 Vol 4 No 2 (2019): September 2019 Vol 4 No 1 (2019): March 2019 Vol 3 No 2 (2018): September 2018 Vol 3 No 1 (2018): March 2018 Vol 2 No 2 (2017): September 2017 Vol 2 No 1 (2017): March 2017 Vol 1 No 2 (2016): September 2016 Vol 1 No 1 (2016): March, 2016 More Issue