Pengenalan Angka Tulisan Tangan Menggunakan Diagonal Feature Extraction dan Artificial Neural Network Multilayer Perceptron

M. Ardi Firmansyah, Kurniawan Nur Ramadhani, Anditya Arifianto

Abstract


Pada  penelitian  ini  dibangun  sistem pengenalan angka tulisan tangan menggunakan metode ekstraksi ciri diagonal  dan  Artificial Neural Network Multilayer Perceptron. Pada ekstraksi ciri diagonal, citra dibagi menjadi beberapa area yang sama besar. Pada tiap area dihitung rata-rata nilai piksel pada setiap diagonalnya kemudian dirata-ratakan untuk mendapatkan nilai ciri pada area tersebut.  Ciri diagonal dikombinasikan dengan nilai rata-rata horizontal dan  vertikal  pada  matriks  area  tersebut  untuk  memperkuat  informasi  pada citra. Metode  ini  mencapai  akurasi  sebesar  92.80%  pada  tahap  pengujian menggunakan  1000  dataset  C1  dan  92.60%  pada  tahap  pengujian  menggunakan 1000 dataset MNIST. Kombinasi fitur diagonal dan rata-rata horizontal menghasilkan akurasi tertinggi dalam mengenali angka tulisan tangan.


Full Text:

PDF

References


Gonzalez, R. C., Woods, R. W. (2002). Digital Image Processing. Education. https://doi.org/10.1049/ep.1978.0474

Jindal, A., Dhir, R., & Rani, R. (2012). Diagonal Features and SVM Classifier for Handwritten Gurumukhi Character Recognition. International Journal of Advanced Research in Computer Science and Software Engineering, 2(5), 505–508.

LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), 2278–2323. https://doi.org/10.1109/5.726791

Pradeep, J., Srinivasan, E., & Himavathi, S. (2010). Diagonal Feature Extraction Based Handwritten Character System Using Neural Network. International Journal of Computer Applications, 8(9), 17–22. https://doi.org/10.5120/1236-1693

Rajashekararadhya, S. V., & Ranjan, P. V. (2009). Zone based Feature Extraction Algorithm for Handwritten Numeral Recognition of Kannada Script, (March), 6–7.

Singh, G., & Sachan, M. (2015). Multi-layer perceptron (MLP) neural network technique for offline handwritten Gurmukhi character recognition. 2014 IEEE International Conference on Computational Intelligence and Computing Research, IEEE ICCIC 2014, 1–5. https://doi.org/10.1109/ICCIC.2014.7238334

Stehman, S. V. (1997). Selecting and interpreting measures of thematic classification accuracy. Remote Sensing of Environment, 62(1), 77–89. https://doi.org/10.1016/S0034-4257(97)00083-7




DOI: http://dx.doi.org/10.21108/INDOJC.2018.3.1.214

Refbacks

  • There are currently no refbacks.


Copyright (c) 2018 M. Ardi Firmansyah, Kurniawan Nur Ramadhani, Anditya Arifianto

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.