Recognition of Javanese Month Names Written in Javanese Script Using The Backpropagation Method and Wavelet Transform Feature Extraction
Keywords:
Javanese Script, Artificial Neural Network, Wavelet Transform, Word RecognitionAbstract
Javanese script is one of Indonesia's cultural heritages. It was once widely used as a means of communication, but as time has progressed, Javanese script has come to be used far less. This decline reflects a decrease in public interest in learning Javanese script. A pattern-recognition model is therefore needed to help a computer system recognize words written in Javanese script. Such a model can be built using the backpropagation neural network method combined with wavelet transform feature extraction. The training data consisted of 560 images collected by the author, divided into 14 classes, while the testing data consisted of handwritten samples from 5 different respondents. The data were first segmented to separate the individual characters; feature extraction was then performed using the wavelet transform, and the resulting features were evaluated with the backpropagation network to determine recognition accuracy. The results show that combining wavelet transform feature extraction with the backpropagation algorithm gives good performance, achieving the highest accuracy of 84.18%, correctly recognizing 181 of 215 test images.
References
[1] Arora, S., Brar, Y. S., Kumar, S. 2014. Haar Wavelet Transform For Solution Of Image Retrieval.International Journal of Advanced and Mathematical Science, vol 5, pp 27-31
[2] Arum, N. B. W. 2016. Pengenalan Pola Aksara Jawa Nglegena berbasis Wavelet dan Jaringan Syaraf Tiruan Backpropagation. Skripsi. Yogyakarta: Universitas Gadjah Mada.
[3] Darusuprapta, Harjana, H. S. U., Nursatwika, Subalidinata, Hadiatmadja, S. 2002. Pedoman Penulisan Aksara Jawa. Yogyakarta: Yayasan Pustaka Nusatama.
[4] Fausett, L. 1994. Fundamentals of Neural Networks Architectures, Algorithms, and Applications. London: Prentice Hall, Inc.
[5] Firdausi, A. I. 2019. Pengenalan Wajah dengan Algoritma Backpropagation Berdasarkan Transformasi Wavelet Diskrit. Skripsi. Jember: Universitas Jember.
[6] Sabri. A. 2016. Pengolahan Citra. Depok: Universitas Gunadarma.
[7] Weisling, Daphne, E. J. 2011. Pembangunan Aplikasi Pengenalan Citra Aksara Jawa Menggunakan Metode Backpropagation Dengan Wavelet Sebagai Pemrosesan Awal Citra. Skripsi. Yogyakarta. Universitas Atma Jaya Yogyakarta.
[8] Wibowo, A. 2012. Pengenalan Huruf Jawa Tulisan Tangan Menggunakan Jaringan Saraf Tiruan Perambatan Balik Dengan Fuzzy Feature Extraction. Skripsi. Semarang: Universitas Diponegoro.
[9] Wibowo, A. T. 2018. Pengenalan Pola Tulisan Tangan Aksara Jawa dengan Algoritma Backpropagation. Skripsi. Yogyakarta: Universitas Sanata Dharma
[10] Wijaya, I. G. P. S. dan Bulkis K. 2004. Pengenalan Citra Sidik Jari Berbasis Transformasi Wavelet dan Jaringan Syaraf Tiruan. Universitas Mataram: Departemen Teknik Elektro. 46-52.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Kafiyanto Hanafi Yahya, Ahmad Kamsyakawuni, Abduh Riski (Author)
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
