Document Type


Publication Date



This introduces the Boise State Bangla Handwriting Dataset, a publicly accessible offline handwriting dataset of Bangla script. This can be found at

A basic character recognition method is presented where the features are extracted based on zonal pixel counts, structural strokes and grid points with U-SURF descriptors modeled with bag of features.

Benchmarking with this approach on 3 other publicly available Bangla datasets is reported. The highest classification accuracy obtained with an SVM classifier based on a cubic kernel is 96.8%.

Copyright Statement

© Nishatul Majid and Elisa H. Barney Smith, 2018.