Improvement accuracy of recognition isolated Balinese characters with Deep Convolution Neural Network

Ida Bagus Teguh Teja Murti


The numbers of Balinese script and the low quality of palm leaf manuscripts provide a challenge for testing and evaluation for character recognition. The aim of high accuracy for character recognition of Balinese script,we implementation Deep Convolution Neural Network using SmallerVGG (Visual Geometry Group) Architectur for character recognition on palm leaf manuscripts. We evaluated the performance that methods and we get accuracy 87,23% .

Full Text:



D. Cireşan, U. Meier, dan J. Schmidhuber, “Multi-column Deep Neural Networks for Image Classification,†Feb 2012.

C. L. Liu, F. Yin, D. H. Wang, dan Q. F. Wang, “Online and offline handwritten Chinese character recognition: Benchmarking on new databases,†Pattern Recognit., vol. 46, no. 1, hal. 155–162, 2013.

M. W. A. Kesiman, S. Prum, J. C. Burie, dan J. M. Ogier, “An initial study on the construction of ground truth binarized images of ancient palm leaf manuscripts,†Proc. Int. Conf. Doc. Anal. Recognition, ICDAR, vol. 2015–Novem, hal. 656–660, 2015.

M. W. A. Kesiman, S. Prum, J. C. Burie, dan J. M. Ogier, “Study on feature extraction methods for character recognition of Balinese script on palm leaf manuscript images,†Proc. - Int. Conf. Pattern Recognit., hal. 4017–4022, 2017.

K. Simonyan dan A. Zisserman, “Very Deep Convolutional Networks for Large-Scale Image Recognition,†Sep 2014.

M. Z. Alom, P. Sidike, M. Hasan, T. M. Taha, dan V. K. Asari, “Handwritten Bangla Character Recognition Using the State-of-the-Art Deep Convolutional Neural Networks,†Comput. Intell. Neurosci., vol. 2018, hal. 1–12, 2018.


Article Metrics

Abstract view : 121 times
PDF - 76 times


  • There are currently no refbacks.

Flag Counter

Journal of Applied Intelligent System (e-ISSN : 2502-9401p-ISSN : 2503-0493) is published by Department of Informatics Universitas Dian Nuswantoro Semarang.


Journal of Applied Intelligent System indexed by :

This journal is under licensed of Creative Commons Attribution 4.0 International License.