This repository is an unofficial implementation from paper DeepLontar: Handwritten Balinese Character Detection and Syllable Recognition on Lontar Manuscript published in Nature - Scientific Data.
DeepLontar is dataset for handwritten Balinese character detection and syllable recognition on lontar manuscript. Lontar manuscript was collected from libraries at universities in Bali. Data generation was carried out to produce 600 Lontar images to increase the variety of data. Annotations were conducted to label each character resulting in more than 100,000 characters in 55 character classes. This dataset can be used to train and evaluate performance in detecting and recognizing new Lontar manuscripts. Dataset DeepLontar is available here: https://doi.org/10.6084/m9.figshare.20103803.v2
