ENSEMBLING DEEP CONVOLUTIONAL NEURAL NEWORKS FOR BALINESE HANDWRITTEN CHARACTER RECOGNITION

While deep learning has proven its performance in various problems and applications, it also opens opportunities a new way to promote the heterogeneity of cultures heritages. Balinese script is cultural heritage Bali, where used write on palm-leaf manuscripts contains essential information. Most were damaged due age lack maintenance, so digitalization technique should be developed. In this study, we propose an ensemble convolutional neural networks recognize handwritten characters script. We extensively compared network architectures, results showed that our methods achieved state art.