A New Deep Learning-Based Mobile Application for Komering Character Recognition

Kunang, Yesi Novaria; Yadi, Ilman Zuhri; Mahmud, M. A.; Husin, Mansyur

doi:10.1109/isriti56927.2022.10053072

Cited by 2 publications

(9 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The first stage involves generating testing data using augmentation techniques to create various script image variations. For the dataset, samples of Komering characters were obtained from previous research [2], [22]. This dataset selected five characters (RHU-GHU, SU, TU, WU, and YU), as shown in Figure 2.…”

Section: Methodsmentioning

confidence: 99%

“…Wulan Sapitri 1 , Yesi Novaria Kunang 2 , Ilman Zuhri Yadi 3 , Mahmud 4 that it can reduce the gap between the training, validation, and testing datasets, making the dataset more representative and resulting in a more accurate model while reducing overfitting [6]- [9]. The fundamental concept of data augmentation is to create a dataset that covers new variations in input while maintaining the correct labels [10].…”

Section: The Impact Of Data Augmentation Techniques On the Recognitio...mentioning

confidence: 99%

“…To preserve ancient scripts like the Komering script some researchers have used technology to preserve the Komering script, such as deep learning [1], [2]. However, one of the challenges of a deep learning model is that it is trained to recognize images with a limited amount of data.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

The Impact of Data Augmentation Techniques on the Recognition of Script Images in Deep Learning Models

Sapitri,

Kunang,

Yadi

et al. 2023

join

View full text Add to dashboard Cite

Deep learning technology is widely used for recognizing character images, including various regional characters and diverse ancient scripts. Deep learning models require large data sets to recognize images accurately. However, creating a dataset has limitations in terms of quantity, including the Komering script dataset used in this study. Data augmentation techniques can be applied to expand the dataset by modifying existing images to increase data diversity. This study aims to investigate the impact of augmentation techniques on the performance of deep learning models in the case of Komering script recognition. The dataset consists of 500 images for five classes of Komering script characters. Three augmentation techniques, namely random rotation, height shift, and width shift, were applied to the five characters, which were then used to test the model trained to recognize characters in the Komering dataset. This research contributes to providing insights into the effect of augmentation techniques on robust confidence prediction of deep learning models for recognizing newly augmented data. The results demonstrate that the deep learning model can recognize modified data using augmentation techniques with an average accuracy of 80.05%.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: The Impact Of Data Augmentation Techniques On the Recognitio...mentioning

confidence: 99%

See 1 more Smart Citation

The Impact of Data Augmentation Techniques on the Recognition of Script Images in Deep Learning Models

Sapitri,

Kunang,

Yadi

et al. 2023

join

View full text Add to dashboard Cite

show abstract

“…(2022) mengembangkan aplikasi pengenalan karakter aksara Komering menggunakan model Convolutional Neural Network (CNN) dengan akurasi 96% untuk mengenali tulisan tangan dan 100% untuk gambar dari masukan foto. Pada penelitian ini aplikasi yang dikembangkan belum dilengkapi dengan transliterasi aksara latin ke Ulu [15].…”

Section: Pendahuluanunclassified

“…Dalam penelitian kunang dkk. (2022), pra-pemrosesan data dilakukan melalui beberapa tahapan, yaitu scanning, cutting, dan pelabelan [15]. Salah satu contoh dataset yang telah dilakukan dalam penelitian tersebut dapat dilihat pada Gambar 5 berikut yang diambil dari https://bit.ly/scan-komering [21].…”

Section: Pra-pemrosesanunclassified

Pengembangan Aplikasi Transliterasi Teks Latin ke Aksara Ulu (Komering) Berbasis Web

Permata Sari,

Novaria Kunang

2023

processor

View full text Add to dashboard Cite

Aksara Ulu adalah salah satu huruf atau jenis tulisan yang digunakan dan dikembangkan oleh masyarakat Sumatera Selatan yakni etnis Serawai, Lembak, Rejang, dan Pasemah. Umumnya aksara Ulu ini digunakan untuk kegiatan sehari-hari, seperti bercerita, menulis sajak dan mencatat hukum adat. Aksara Ulu perlu dilestarikan karena penggunaannya saat ini makin berkurang seiring diperkenalkannya penulisan Latin yang menjadi standar dunia internasional. Untuk melestarikan aksara Ulu, maka diperlukan sebuah alat bantu yang dapat membantu dalam mengalihaksarakan teks Latin ke aksara Ulu. Sehingga pada penelitian ini dimaksudkan untuk mengembangkan aplikasi transliterasi teks latin ke aksara Ulu berbasis web dengan menggunakan teknik mapping dan algoritma sequential search. Aplikasi yang dihasilkan dapat membantu dan mempermudah pengguna dalam melakukan transliterasi dari teks Latin ke aksara Ulu.

show abstract

A New Deep Learning-Based Mobile Application for Komering Character Recognition

Cited by 2 publications

References 6 publications

The Impact of Data Augmentation Techniques on the Recognition of Script Images in Deep Learning Models

The Impact of Data Augmentation Techniques on the Recognition of Script Images in Deep Learning Models

Pengembangan Aplikasi Transliterasi Teks Latin ke Aksara Ulu (Komering) Berbasis Web

Contact Info

Product

Resources

About