Balinese Script Handwriting Recognition Using Faster R-CNN
Dublin Core
Title
Balinese Script Handwriting Recognition Using Faster R-CNN
Subject
balinese script; faster R-CNN; handwriting
Description
In Balinese culture, the ability to read Balinese script is one of the challenges young generations face. Advances in machine
learning have proposed handwriting detection systems using both traditional and deep learning models. However, the
traditional approach is usually impractical and is prone to inaccurate identification results. Convolutional Neural Network
(CNN)-based models integrate feature extraction and classification into an end-to-end pipeline to increase performance. This
research proposes that recognizing characters through an object detection approach makes an end-to-end process of localizing
and classifying several characters simultaneously using the Faster R-CNN. Four CNN models, including ResNet-50, ResNet-
101, ResNet-152, and Inception ResNet V2 were tested to detect 28 Balinese characters in a single form covering 18 consonants
and 10 digits using Intersection over Union (IoU) thresholds: 0.5 and 0.75. ResNet-50 and Inception ResNet V2 achieve 0.991
mAP at IoU of 0.5, while Inception ResNet V2 excels at IoU of 0.75. Further analysis showed that class “nol” had the lowest
Recall due to many undetected ground truths. Meanwhile, class “ba” had the lowest Precision due to its similarity with classes
“ga” and “nga”. This research contributes to experimenting with Faster R-CNN in detecting handwritten Balinese scripts.
learning have proposed handwriting detection systems using both traditional and deep learning models. However, the
traditional approach is usually impractical and is prone to inaccurate identification results. Convolutional Neural Network
(CNN)-based models integrate feature extraction and classification into an end-to-end pipeline to increase performance. This
research proposes that recognizing characters through an object detection approach makes an end-to-end process of localizing
and classifying several characters simultaneously using the Faster R-CNN. Four CNN models, including ResNet-50, ResNet-
101, ResNet-152, and Inception ResNet V2 were tested to detect 28 Balinese characters in a single form covering 18 consonants
and 10 digits using Intersection over Union (IoU) thresholds: 0.5 and 0.75. ResNet-50 and Inception ResNet V2 achieve 0.991
mAP at IoU of 0.5, while Inception ResNet V2 excels at IoU of 0.75. Further analysis showed that class “nol” had the lowest
Recall due to many undetected ground truths. Meanwhile, class “ba” had the lowest Precision due to its similarity with classes
“ga” and “nga”. This research contributes to experimenting with Faster R-CNN in detecting handwritten Balinese scripts.
Creator
Alif Adwitiya Pratama, Mahmud Dwi Sulistiyo, Aditya Firman Ihsan
Source
http://jurnal.iaii.or.id
Publisher
Professional Organization Ikatan Ahli Informatika Indonesia (IAII)/Indonesian Informatics Experts Association
Date
December 2023
Contributor
Sri Wahyuni
Rights
ISSN Media Electronic: 2580-0760
Format
PDF
Language
English
Type
Text
Files
Collection
Citation
Alif Adwitiya Pratama, Mahmud Dwi Sulistiyo, Aditya Firman Ihsan, “Balinese Script Handwriting Recognition Using Faster R-CNN,” Repository Horizon University Indonesia, accessed January 12, 2026, https://repository.horizon.ac.id/items/show/10154.