Klasifikasi Akasara Jawa Dengan CNN


  • Edo Prasetyo N. A Wijaya Institut Sains dan Teknologi terpadu Surabaya




Classification, Convolution Neural Network, Javanesse Letter


It is common knowledge that CNN is a significant method in image classification. This is because CNN can classify Latin letters with a high degree of accuracy. Lenet5 in CNN is tasked with converting 2D features from an image into a convolutional network continuously. CNN architecture consists of several layers, including the Convolution Layer, Relu layer, Subsampling layer, Fully Connected Layer. In this research, CNN is used to classify Javanese script images into 20 classes. These classes include ha, na, ca, ra, ka, da, ta, wa, la, pa, dha, ja, yes, nya, ma, ga, ba, tha, nga. Javanese script used in this research is Ngalena Javanese script. The precision values for each class range from 0.5 to 0.6.


Download data is not yet available.


A. Rita Widiarti and P. Nari Wastu, "Javanese Character Recognition Using Hidden Markov Model," International Science Index, Computer and Information Engineering Vol:3, No:9, 2009.

Bishwajit Purkaystha, Tapos Datta and Md Saiful Islam, “Bengali Handwritten Character Recognition Using Deep Convolutional Neural Network,†2017 20th International Conference of Computer and Information Technology. ICCIT 2017.

Huiqun Deng, George Stathopoulos, and Ching Y. Suen, "Applying Error-Correcting Output Coding to Enhance Convolutional Neural Network for Target Detection and Pattern Recognition",International Conference on Pattern Recognition. 2010.

Kietikul Jearanaitanakij and Ouen Pinngern “Hidden Unit Reduction of Artificial Neural Network on English Capital Letter Recognition†IEEE, 2006, doi: 1-4244-0023-6/06/$20.00.

Kun Guo, Ning Li, “Research on Classification of Architectural Style Image Based on Convolution Neural Network,†2017 IEEE, doi: 978-1-5090-5363-6/17/$31.00.

Phatthanaphong Chomphuwiset “Printed Thai Character Segmentation and Recognition,†2017 4th IEEE International Conference on Soft Computing and Machine Intelligence.

Rismiyati, Khadijah, and A. Nurhadiyatna, “Deep learning for handwritten Javanese character recognition,†Proc. - 2017 1st Int. Conf. Informatics Comput. Sci. ICICoS 2017, vol. 2018-January, pp. 59–63, 2018, doi: 10.1109/ICICOS.2017.8276338.

Roshan Fernandes and Anisha P Rodrigues, “Kannada Handwritten Script Recognition using Machine Learning Techniques,†2019 IEEE, doi: 978-1-7281-3735-3/19/$31.00.

T. Septianto, E. Setyati, and J. Santoso, “Digit Classification of Majapahit Relic Inscription using GLCM-SVM,†vol. 1, no. 2, pp. 46–54, 2018.

PlumX Metrics



How to Cite

Wijaya, E. P. N. A. (2020). Klasifikasi Akasara Jawa Dengan CNN. Jurnal Teknika, 12(2), 61–64. https://doi.org/10.30736/jt.v13i2.479



Jurnal Teknika