Preprint
Aug 2026
BanglaWild: An In-the-Wild Bengali Scene Text Recognition Benchmark for OCR and Vision-Language Models
This work introduces BANGLAWILD, a benchmark of 2,535 Bengali scene text images, each paired with a verbatim gold transcription, two categorical axes, four diagnostic attributes, and an orthographically standard form where the in-image text deviates from canonical spelling.
Sadab Shiper, Tawsif Tashwar Dipto, M. Inzamam et al.
· 0 citations