Implementation Convolutional Neural Network (CNN) for Bima Script Handwriting Recognition

Indonesia has a wide variety of languages. In the dialect of a region, there are letter symbols that represent the expression of the region's unique language. One example of a language that shows unique characteristics in its writing system is Bima, known as the Bima script. Bima script, or Mbojo script, is a writing system traditionally used in the Bima region, located in West Nusa Tenggara Province. Bima script is still not widespread among the public, so it is important to preserve it as part of the cultural heritage of the Mbojo tribe. This research aims to train a computer to recognize Bima characters using the Convolutional Neural Network method. The dataset used consists of 2640 images of Bima script handwriting with 22 classes. The results showed a reliable performance of the CNN model, with an accuracy of 97,34%, precision 97,56%, recall 97,34%, and f1-score 97,31% on the test data.