Riansyah, Rizki Rahmat and Nurhasanah, Youllia Indrawaty and Dewi, Irma Amelia (2017) Sistem Pengenalan Aksara Sunda Menggunakan Metode Modified Direction Feature Dan Learning Vector Quantization. Jurnal Teknik Informatika dan Sistem Informasi, 3 (1). pp. 17-30. ISSN e-ISSN : 2443-2229

Preview

Text Sistem Pengenalan Aksara Sunda Menggunakan Metode Modified Direction Feature Dan Learning Vector Quantization.pdf Download (1MB) | Preview

Abstract

Sundanese script is one local Indonesian script which has the specificity in terms of how the writing system by using a non-latin character as well as in terms of the unique pronunciation, therefore that presence should be conserved. One of its preservation are to build an sundanese recognition system. This system will accept input in the image of sundanese script that will be processed in order to generate output in the form of text. In the process of recognizing a pattern from the image of sundanese script can use the techniques of extraction feature, one of which is modified direction feature (MDF), whereas the methods used for classification and identification process is learning vector quntization (LVQ). To support it’s function of this image recognition system combined with text to speech (TTS). TTS system is a system that can convert text into speech, so the output of this system can display text results of sundanese recognition script along with the examples of pronunciation. The level of accuracy of the test results of the 300 samples data image of sundanese script verified correctly between the suitability of image characters with the names and the pronunciation is 78.67%.

Actions (login required)

View Item