Handwritten Balinese Script Recognition on Palm Leaf Manuscript using Projection Profile and K-Nearest Neighbor

This paper presents a simple approach to the handwritten Balinese script characters recognition in palm-leaf lontar manuscripts. The Lontar manuscript is one of cultural heritages found Bali. manuscripts are written using pengrupak, which kind knife for writing on palm leaves. To give color results writing, candlenut used so that appears clear. In this paper, we apply projection profile at segmentation stage get manuscript. leaf use Wariga Palalubangan leaf. process carried out by implementing K-Nearest Neighbor process. was made Wianjana obtained from 720 images consisting 18 classes as dataset training. test showed level accuracy 52% scripts derived and 92% paper.