Corrected public release of the Kurdish scene-text recognition resource associated with KSTRV1. The multilingual collection covers Sorani and Badini in Arabic-based Kurdish script alongside Arabic and English. KSTRV2 corrects Unicode and annotation issues in the deprecated first version.
Natural scene images, word crops, synthetic text instances, text transcriptions, bounding boxes, language and orientation annotations, and split files.
Sardar Omar Salih , Karwan Jacksi (2025)
This Data in Brief article introduces a scene-text dataset covering Kurdish Sorani and Badini in Arabic-based script alongside Arabic and English. It reports 1,420 natural scene images, 19,872 real …