DeepLontar dataset for handwritten Balinese character detection and syllable recognition on Lontar manuscript.

ABSTRACT: The digitalization of traditional Palmyra manuscripts, such as Lontar, is the government's main focus in efforts to preserve Balinese culture. Digitization is done by acquiring Lontar manuscripts through photos or scans. To understand Lontar's contents, experts usually carry out transliteration. Automatic transliteration using computer vision is generally carried out in several stages: character detection, character recognition, syllable recognition, and word recognition. Many methods can be used for detection and recognition, but they need data to train and evaluate the resulting model. In compiling the dataset, the data needs to be processed and labelled. This paper presented data collection and building datasets for detection and recognition tasks. Lontar was collected from libraries at

SUBMITTER: Siahaan D 

PROVIDER: S-EPMC9741579 | biostudies-literature | 2022 Dec

REPOSITORIES: biostudies-literature