Updates
Source code:
View IndicPhotoOCR on GitHub
Updates
Recent milestones in models, language support, demos, and documentation.
May 2026
Paper accepted for publication in International Journal on Document Analysis and Recognition (IJDAR) and oral presentation at ICDAR 2026 in Vienna.
August 2025
Project page launched.
April 2025
Documentation page launched with Sphinx.
March 2025
Hugging Face demo extended to 12 languages.
February 2025
Added tri-lingual and 12-class script identification models, plus recognition models for Malayalam and Kannada.
January 2025
Added ViT-based script identification models and a Hugging Face demo for bilingual Hindi and English scenes.
December 2024
Added the TextBPN++ detection module.
November 2024
Released code through Google Colab and added recognition support for 10 languages.
September 2024
Repository created.