Pengenalan Aksara Bali Menggunakan Metode Pyramid Histogram of Oriented Gradients
DOI:
https://doi.org/10.34818/INDOJC.2020.5.1.378Abstract
Aksara Bali terdiri dari 18 aksara dasar (biasa disebut aksara Wianjana) yang masing-masing terdiri atas 7 aksara vokal (pengangge suara). Penulisan aksara Bali dapat ditulis pada kertas ataupun daun tal yang sudah dikeringkan dan memiliki tekstur yang kasar serta mudah sobek sehingga membuat sulit dibaca. Maka dari itu, dibuat sistem yang dapat mengenali aksara Bali pada daun tal untuk membantu dapat membaca aksara Bali. Sistem ini dibangun menggunakan metode Pyramid Histogram of Oriented Gradient (PHOG) sebagai metode ekstraksi ciri. Dataset yang digunakan adalah dataset dari AMADI Lontar Set yang berupa gambar berjumlah 19.383 gambar dengan 133 kelas. Pada pengujian didapatkan nilai f1-score terbaik pada PHOG level 3 dengan 6 bin orientasi dan klasifikasi menggunakan SVM kernel linear yaitu sebesar 66.49% dan akurasi sebesar 81.35%.Downloads
References
"Basabali," [Online]. Available: https://basabali.org/balinese-script/introduction-to-aksara-bali/. [Accessed 2018].
M. S. A. a. M. A. Sudarma, "Balinese Script’s Character Reconstruction Using Linear Discriminant Analysis," Indonesian Journal of Electrical Engineering and Computer Science (IJEECS), vol. 4, no. 2, p. 479, 2016.
M. a. I. W. A. S. Sudarma, "The Identification of Balinese Scripts' Characters based on Semantic Feature and K Nearest Neighbor," International Journal of Computer Applications, vol. 1, p. 91, 2014.
M. W. A. B. J. C. W. G. N. M. A. S. I. M. G. &. O. J. M. Kesiman, "AMADI_LontarSet: The First Handwritten Balinese Palm Leaf Manuscripts Dataset," in 15th International Conference on Frontiers in Handwriting Recognition (ICFHR), 2016.
S. a. A. L. Khorashadizadeh, "Arabic/Farsi Handwritten Digit Recognition usin Histogra of Oriented Gradient and Chain Code Histogram," International Arab Journal of Information Technology (IAJIT), vol. 4, p. 13, 2016.
P. M. a. R. S. H. Kamble, "Handwritten Marathi character recognition using R-HOG Feature," in International Conference on Advanced Computing Technologies and Applications (ICACTA), 2015.
R. a. M. J. Ebrahimzadeh, "Efficient handwritten digit recognition based on histogram of oriented gradients and svm," International Journal of Computer Applications, vol. 9, p. 104, 2014.
G. H. N. a. T. A. B. W. Nugraha, "Pengenalan Isyarat Tangan Menggunakan Algoritma Pyramidal Lucas Kanade Dan Histogram Of Oriented Gradients," eProceedings of Engineering, Bandung, 2015.
L. N. A. W. W. a. R. C. W. Harfiya, "Offline signature verification based on pyramid histogram of oriented gradient features," in 1st International Conference on Informatics and Computational Sciences (ICICoS), 2017.
A. Ghandehari, M. Anvaripour and Sima, "Palmprint verification and identification using pyramidal HOG feature and fast tree based matching.," in 2012 5th IAPR International Conference on Biometrics (ICB), 2012.
Downloads
Published
How to Cite
Issue
Section
License
- Manuscript submitted to IndoJC has to be an original work of the author(s), contains no element of plagiarism, and has never been published or is not being considered for publication in other journals.Â
- Copyright on any article is retained by the author(s). Regarding copyright transfers please see below.
- Authors grant IndoJC a license to publish the article and identify itself as the original publisher.
- Authors grant IndoJC commercial rights to produce hardcopy volumes of the journal for sale to libraries and individuals.
- Authors grant any third party the right to use the article freely as long as its original authors and citation details are identified.
- The article and any associated published material is distributed under the Creative Commons Attribution 4.0License
