A hybrid feature extraction method for accuracy improvement in "Aksara Lontara" translation

Abstract

An Optical Character Recognition (OCR) of "Aksara Lontara" has been constructed using a novel combination of feature extraction methods in this study. The ancient font of "Lontara" is then translated into Bahasa Indonesia to help non-native language to learn this language. Two powerful extraction feature methods, i.e., Modified Direction Feature (MDF) and Fourier Descriptor (FD) are stages combined to deal with two dominant phases of the Lontara font. The classification process is conducted using Support Vector Machine (SVM) as a fast and straightforward learning method deal with 23 fonts in image containing of 150×120 pixels. In this research, 50 verbs were used for training and 30 verbs for validating the system. The results show that system can reach 96% accuracy using this hybrid in extraction feature with kernel variable of C = 3 and σ = 8.