Fixing duplicate detection results in KotenOCR's modern-script OCR mode (NDLOCR-Lite) by adding NMS and filtering to line_* classes, achieving detection accuracy on par with the reference ndlocr-lite implementation.
KotenOCR v1.3.0 adds NDLOCR-Lite support for modern printed text OCR alongside the existing classical text (kuzushiji) mode, with one-tap mode switching and parallelized recognition for up to 6.7x speedup.
KotenOCR is a free iOS app that runs the NDL Koten OCR-Lite model entirely on-device, enabling offline recognition of kuzushiji (classical Japanese cursive script) from photos.
Building an NDLOCR Gradio App Using Azure Virtual Machines
Created a Gradio app to try ndlocr_cli (NDLOCR ver.2.1) application
Using NDL Classical Book OCR-Lite (ndlkotenocr-lite) on Mac OS
Trying NDLTSR (NDL Table Structure Recognition)
Created Notebooks Using NDLOCR and NDL Classical Japanese OCR ver.2
Running NDL Classical Japanese OCR on mdx
Conversion and Visualization of the NDL-DocL Dataset (Document Image Layout Dataset)
NDL OCR Now Supports Ruby (Furigana) Text Extraction