Akhter S and Rege P.
(2021). Multi-task learning for pre-processing of printed Devanagari document images with hyper-parameter optimization of the deep architecture using Taguchi method. Sādhanā. 10.1007/s12046-021-01664-7. 46:3. Online publication date: 1-Sep-2021.https://link.springer.com/10.1007/s12046-021-01664-7