Analysis and Implementation of CNN in Real- time Classification and Translation of Kanji Characters


  • Putri Annisa Universitas Muhammadiyah Sumatera Utara
  • Zuli Agustina Gultom Universitas Muhammadiyah Sumatera Utara
  • Yoshida Sary Universitas Muhammadiyah Sumatera Utara




CNN, Kanji Characters, OCR, Real-time classification, Digital Image


This research explores the training outcomes of the Convolutional Neural Network (CNN) algorithm applied to Kanji character recognition. It employs a CNN architecture with 10 layers for recognizing digital image of Kanji characters from N5 to N1 levels. The training of the CNN model reveals varying accuracies, influenced by factors such as architecture, training data size, and data quality. The lowest accuracy, occurring at the beginning of training, highlights challenges like poor random weight initialization and suboptimal architecture. Conversely, the highest accuracy demonstrates the optimal predictive ability of the model after multiple training iterations. The iterative training process refines the model's accuracy over time, with initial challenges paving the way for a better understanding of the data for future improvements. In the subsequent analysis and system development phase, two algorithms are compared to assess the effectiveness of the CNN algorithm in Kanji character recognition. Testing is conducted at various complexity levels to systematically evaluate accuracy. This testing involves complexity levels at each Kanji character level to assess system accuracy. The developed model shows potential for real-time classification of Kanji characters, with a focus on error rate and accuracy during training and testing. The built model can essentially be used to evaluate the ability to recognize Kanji characters effectively. The model's performance can be assessed based on the error rate and accuracy achieved during the training and testing processes.

GS Cited Analysis


Download data is not yet available.


Afif, M., Fawwaz, A., Ramadhani, K. N., & Sthevanie, F. (2020). Breed Classification in Cats using Convolutional Neural Network (CNN). Journal of Final Project Faculty of Informatics, 8 (1), 715–730.

Andrian, R., Naufal, M. A., Hermanto, B., Junaidi, A., & Lumbanraja, F. R. (2019). K-Nearest Neighbor (K-NN) Classification for Recognition of the Batik Lampung Motifs. Journal of Physics: Conference Series, 1338 (1), 012061. doi:10.1088/1742-6596/1338/1/012061.

Coates, Adam. Honglak L., & Andrew Y.Ng. (2011). An Analysis of the Singe Layer Network in Unsupervised Feature Learning. Amerika Serikat: Stanford University.

Fukushima, K. (1980). Neocognitron: A Self-Organizing Neural Network Model for a Mechanism of Pattern Recognition Unaffected by Shift in Position. Biological Cybernetics.

Goodfellow, I., Bengio, Y, & Courville, A. (2016). Deep Learning (Adaptive Computation and Machine Learning Series). The MIT Press.

Hanin, M. A., Patmasari, R., & Nur, R. Y. (2021). Skin Disease Classification System Using Convolutional Neural Network (CNN). E-Proceeding Engineering, 8 (1), 273–281.

Nurtantio, M. P., & Sutojo, T. (2017). Digital Image Processing. ANDI (Member of IKAPI). Renariah. (2004). Mengingat Kanji melalui Bushu. Jurnal Fokus, 1 (2), 1-1.

Suartika, I. W., E. P., Wijaya, A. Y., & Soelaiman, R. (2016). Image Classification Using Convolutional Neural Network (CNN) on Caltech 101. JTITS, 5(1), doi:10.12962/j23373539.v5i1.15696.

Setiawan, W. (2020). Deep Learning using Convolutional Neural Network. Media Nusa Creative.

Tjokorda Agung Budi. (2014). Pengenalan Karakter Huruf Hangul Korea Menggunakan Random Forest. E- Proceeding of Engineering, Vol. 1 (1), 755-763.


Crossmark Updates

How to Cite

Annisa, P. ., Gultom, Z. A. ., & Sary, Y. . (2024). Analysis and Implementation of CNN in Real- time Classification and Translation of Kanji Characters. Sinkron : Jurnal Dan Penelitian Teknik Informatika, 9(1), 296-305.