IIIT Hyderabad Publications |
|||||||||
|
HInDoLA: A Cloud-based System for Large-Scale Annotation and Analysis of Indic Palm Leaf ManuscriptsAuthors: Abhishek Trivedi,Ravi Kiran Sarvadevabhatla Conference: 15th International Conference on Document Analysis and Recognition (ICDAR 2019 2019) Location Sydney, Australia Date: 2019-09-20 Report no: IIIT/TR/2019/68 AbstractPalm-leaf manuscripts are one of the oldest medium of inscription in many Asian countries. Especially, manuscripts from the Indian subcontinent form an important part of the world’s literary and cultural heritage. Despite their significance, large-scale datasets for layout parsing and targeted annotation systems do not exist. Addressing this, we propose a web-based layout annotation and analytics system. Our system, called HInDoLA, features an intuitive annotation GUI, a graphical analytics dashboard and interfaces with machine-learning based intelligent modules on the backend. HInDoLA has successfully helped us create the first ever large-scale dataset for layout parsing of Indic palm-leaf manuscripts. These manuscripts, in turn, have been used to train and deploy deep-learning based modules for fully automatic and semi-automatic instance-level layout parsing Full paper: pdf Centre for Visual Information Technology |
||||||||
Copyright © 2009 - IIIT Hyderabad. All Rights Reserved. |