Klasifikasi citra HSV aksara kuno pada prasasti tembaga Kintamani menggunakan GLRCM dan SVM

Christina Purnama Yanti (STMIK STIKOM Indonesia)
I Gede Andika (STMIK STIKOM Indonesia)

Jurnal Teknologi dan Sistem Komputer
Volume 8, Issue 2, Year 2020 (April 2020)

The problem of inscription physical damage as one of the historical heritages can be overcome using an image processing technique. The purpose of this study is to design a segmentation application for ancient scripts on inscriptions to recognize the character patterns on the inscriptions in digital form. The preprocessing was carried out to convert images from RGB to HSV. The application used the gray level run length matrix (GLRLM) to extract texture features and the support vector machine (SVM) method to classify the results. The inscription image segmentation was carried out through the pattern detection process using the sliding window method. The application obtained 88.32 % of accuracy, 0.87 of precision, and 0.94 of sensitivity.