Pengenalan Aksara Jawi Tulisan Tangan Menggunakan Freemen Chain Code (FCC), Support Vector Machine (SVM) dan Aturan Pengambilan Keputusan

Safrizal ., Fitri Arnia, Rusdha Muharar

Abstract


Jawi is one variant of Arabic script consists of 35 characters. Some of Jawi characters have the same main shape, but different number of dots in different location. Thus, recognition process of Jawi characters can be done by performing a classification based on the main shape. In recognition process, feature extraction plays an important role. In this research, Freeman Chain Code (FCC) was used as feature extraction and Support Vector Machine (SVM) as classifier. Then we apply the decision rules to classifySVMresult into Jawi characters. FCC is used to represent the boundary of Jawi characters into a chain code. Then the chain code is used bySVMto classify the characters into 19 groups. Feature of location and the number of dots are used by decision rules to classify the groups into Jawi characters. The Jawi characters are handwritten and generated by 10 writers from different backgrounds and ages. The recognition rate of this research was 80.00%.

Keywords : Jawi script, handwriting, FCC, SVM, decision rules.


Abstrak—Aksara Jawi merupakan salah satu varian dari aksara Arab yang terdiri dari 35 aksara. Dari 35 aksara Jawi  tersebut terdapat beberapa aksara dengan bentuk bagian utama yang sama namun memiliki letak dan jumlah titik yang berbeda. Karena perbedaan tersebut maka proses pengenalan aksara Jawi dapat dilakukan dengan melakukan klasifikasi berdasarkan perbedaan bentuk bagian utama. Pada penelitian ini Freeman Chain Code (FCC) digunakan sebagai ekstraksi fitur dan Support Vector Machine (SVM). FCC digunakan untuk merepresentasikan garis batas (boundary) aksara Jawi kedalam kode rantai. Kode rantai tersebut diklasifikasi dengan menggunakan SVM kedalam 19 kelompok. Fitur letak titik dan jumlah titik digunakan sebagai aturan pengambilan keputusan terhadap 19 kelompok hasil klasifikasi SVM kedalam aksara Jawi. Aksara Jawi yang digunakan merupakan tulisan tangan dari 10 orang penulis dari berbagai latar belakang dan umur. Tingkat keberhasilan klasifikasi penelitian ini mencapai 80,00%.

Kata Kunci : aksara Jawi, tulisan tangan, FCC, SVM, aturan pengambilan keputusan


Full Text:

PDF

References


H. H. Musa, “Peranan tulisan Jawi dalam perkembangan Islam di Malaysia,” Jurnal pengajian Melayu, jilid 16, 2005.

A. J. B. Borham, “Tulisan Jawi: tulisan serantau,” in Ucaptama Seminar Tulisan Jawi dan Teknologi Peringkat Kebangsaaan 2012 di Dewan Astaka, Universiti Malaysia Pahang., Oct. 18, 2012.

R. Redika, K. Omar, and M. F. Nasrudin, “Handwritten Jawi words recognition using Hidden Markov Models,” in International Symposium on Information Technology,. ITSim 2008., pp 1-5, Aug. 26-28, 2008.

A. Heryanto, M. F. Nasrudin, and K. Omar, “Offline Jawi handwritten recognizer using hybrid artificial neural networks and dynamic programming,” in International Symposium on Information Technology, ITSim 2008., pp 1-5, Aug. 26-28, 2008.

M. F. Nasruddin, M. Petrou, and L. Kotoulas, “Jawi character recognition using the Trace transform,” in Seventh International Conference on Computer Graphics, Imaging and Visualization., pp 151-156, Aug. 7-10, 2010.

R. Rahmadewi dan R. Kurnia, “Klasifikasi Penyakit Paru Berdasarkan Citra Rontgen dengan Metoda Segmentasi Sobel”. Jurnal Nasional Teknik Elektro (JNTE). vol: 5, no. 1, pp.7-12, Mar 2016.

N. Otsu, "A Threshold Selection Method from Gray-Level Histograms," IEEE Transactions on Systems, Man, and Cybernetics, vol. 9, no. 1, pp. 62-66, Jan. 1979.

T. Y. Zhang and C. Y. Suen, "A fast parallel algorithm for thinning digital patterns," Comm. ACM, vol. 27, no. 3, pp. 236-239, 1984.

L. Lam, S. W. Lee, and C. Y. Suen, "Thinning methodologies-a comprehensive survey," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol 14, no. 9, September 1992, page 879, bottom of first column through top of second column.

H. Freeman, “Computer processing of line-drawing images,” ACM Computing Survey, ACM New York, vol. 6, issue 1, pp.57-97, March 1974.

D. Nasien, H. Habibollah, and S. S. Yuhaniz, “Support Vector Machine (SVM) for English handwritten character recognition,” in Second International Conference on Computer Engineering and Applications (ICCEA)., pp 249- 252, May. 19-21, 2010.




DOI: https://doi.org/10.25077/jnte.v5n1.185.2016

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.

JNTE index by:

 

 

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Statistic and Traffic