
IndicSTR12 aims to address the lack of comprehensive datasets for Indian languages by proposing a real dataset and benchmarking STR performance on 12 major Indian languages.


coremsg

indicstr12-a-comprehensive-dataset-for-indic-scene-text-recognition


IndicSTR12: A Comprehensive Dataset for Indic Scene Text Recognition


title_rewrite


The author presents the creation of IndicSTR12, a dataset addressing the lack of comprehensive datasets for Indian languages, aiming to catalyze the development of robust text detection and recognition models.
