Segmentation and recognition of handwritten Lontara characters using convolutional neural network

Abstract

This study presents a technique to recognize handwritten Lontara characters. Lontara character is Indonesia's traditional character which is used mostly in the southern area of Sulawesi during the kingdom era. The work consists of two stages. First, character segmentation of each character in images is achieved with a combination of contour feature and sliding window technique to create a boundary and extract character segments. Second, a Convolutional Neural Network (CNN) is used to recognize or classify the segmented characters. The dataset contains 23 Lontara characters with five combinations of diacritics and one special character, that falls into 139 classes. The result of the conducted experiments on the dataset shows that CNN provides good results - obtaining 96% of accuracy. Also, the result shows a promising result in a combination of segmentation and recognition.

Access to Document

Other files and links

• Link to publication in Scopus

Fingerprint