Overview
On November 26, 2024, NDL Lab released NDL Classical Book OCR-Lite.
https://lab.ndl.go.jp/news/2024/2024-11-26/
This article introduces how to use it on Mac OS.
Usage (Video)
https://www.youtube.com/watch?v=NYv93sJ6WLU
Usage (Text)
Access the following.
https://github.com/ndl-lab/ndlkotenocr-lite/releases/tag/1.0.0
Select the one containing “macos” from the list. Also select the one matching your chip.
Clicking the link downloads “ndlkotenocr-lite_v1.0.0_macos_m1.tar.gz” as shown below.
After extracting by double-clicking, the application “NDLkotenOCR-Lite” is extracted inside a macos folder.
Double-click the application “NDLkotenOCR-Lite” to launch it.
However, on the first run, it cannot be opened with a warning like the following.
Navigate to “Privacy & Security” and click “Open Anyway” to open the application.
As a result, the following launches.
By selecting the processing target and output destination and pressing the “OCR” button, recognition was performed as shown below.
Here, “The Tale of Genji” (held by the University of Tokyo General Library) is used.
The output results generated txt, json, and xml files.
Summary
At this point, reading accuracy is said to decrease by about 2% on average compared to NDL Classical Book OCR ver.3, but I think the ability to perform lightweight OCR processing without a GPU is a significant advantage.
I am grateful to the developers and those involved in the release.