PENGENALAN AKSARA BALI DENGAN PENDEKATAN METODE DIRECTION FEATURE DAN AREA BINARY OBJECT FEATURE

Ni Made Ari Pratiwi, Widi Hapsari, Theresia Herlina R.

Abstract


The rise of technology has been contributing advances to science, and to human being in making jobs far much easier to do, including pattern recognition. This research focused on character recognition by developing a system capable to recognise images of printed Balinese traditional character, which has a distinct feature of having perceptually similar characters, where each others are often differentiated only by a small stroke or a curve.

The system itself took several processes to recognise a character. First, the image containing Balinese characters is preprocessed. Afterwards, two object features are extracted from the image: Direction and Binary Object Area. Both features then tested for similarity using Euclidean distance with the same features already obtained from the control images.

From 573 characters tested to the system, 559 are recognized as characters and 526 are correctly recognized as the right character, which yields an overall accuracy of 91.8%. Recognition results are dependent to character spacing condition.


Keywords


Pengenalan Pola, Direction Feature, Area Binary Object Feature, Preprocessing

Full Text:

PDF

References


Budi, W.T.A., Hermanto, I. G. R., & Novi, R. D. (2009). Pengenalan Huruf Bali Menggunakan Metode Modified Direction Feature (MDF) Dan Learning Vector Quantization (LVQ). Konferensi Nasional Sistem dan Informatika 2009, Bali, 7-12. Diambil dari http://yudiagusta.files.wordpress.com/2009/11/007-012-knsi09-002-pengenalan-huruf-bali-menggunakan-metode-modified-direction-feature-_mdf_-dan-learning-vector-quantization-_lvq_.pdf.

Agustina, A.C., Suwarno, S., Proboyekti, U. (2011). Pengenalan Aksara Jawa Menggunakan Learning Vektor Quantization (LVQ). Jurnal Teknologi Komputer dan Informatika, 7(1), Yogyakarta: Teknik Informatika Universitas Kristen Duta Wacana, 87-96.

Lakshmi, C.V dan Patvardhan,C. (2004). An Optical Character Recognition System For Printed Telugu Text. Pattern Anal Applic, 7:190-204 DOI 10.1007/s1007/s10044-004-0217-2. Springer-Verlag London Limited.

Putra, D. (2010). Pengolahan Citra Digital. Yogyakarta: Penerbit Andi.

Setiawan, A., Wasiswa, S., Basuki, D.K. (2011). Sistem Pengenalan Plat Nomor Mobil Untuk Aplikasi Informasi Karcis Parkir. EEPIS ITS Surabaya. Diambil dari http://repo.eepis-its.edu/1112/.

Sunarya, I.M.G. (2012). Pengenalan Aksara Bali Tercetak Pada Citra Dokumen Menggunakan Multi Layer Perceptron Dengan Pembelajaran Backpropagation (Tesis S2 Ilmu Komputer, Fakultas MIPA, Universitas Gadjah Mada Yogyakarta, 2012).

Sutoyo, T., Mulyanto, E., Suhartono, V., Nurhayati, O.D., & Wijanarto. (2009). Teori Pengolahan Citra Digital. Yogyakarta : Penerbit Andi.

Widiarti, A.R. (2006). Pengenalan Citra Dokumen Sastra Jawa Konsep dan Implementasinya (Tesis S2 Ilmu Komputer, Fakultas MIPA, Universitas Gadjah Mada Yogyakarta, 2012).

Widiarti, A.R. (2007). Segmentasi Citra Dokumen Teks Sastra Jawa Modern Mempergunakan Profil Proyeksi. SIGMA, 10(2), Juli 2007: 167-176.

Wirawan, Made. (2011). Pengenalan Aksara Bali pada Pen Screen Berbasis Jaringan Syaraf Tiruan Backpropagation ( Skripsi S1, Program Studi Teknik Informatika Fakultas Teknologi Informasi Universitas Kristen Duta Wacana,2011), dari SinTA (Sistem Informasi Tugas Akhir).

Zurnawita dan Suar, Z,. (2009). Algoritma Image Thinning. Elektron, 1(1), Politeknik Negeri Padang, 29-37.




DOI: http://dx.doi.org/10.21460/inf.2013.91.142

Refbacks

  • There are currently no refbacks.


Bookmark and Share