jpocr

Japanese OCR via NDLOCR-Lite (National Diet Library). Trigger on 'OCR this image', '日文OCR', 'recognize Japanese text', or any request to extract text from Japanese documents, screenshots, or scanned pages. Best for printed Japanese and vertical text. Also works for English.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "jpocr" with this command: npx skills add realwaynesun/jpocr

jpocr — Japanese OCR Skill

Local Japanese OCR powered by NDLOCR-Lite from Japan's National Diet Library. Runs on CPU (Apple Silicon / x86), no GPU or API key required.

Capabilities

TargetQuality
Printed Japanese (活字)Excellent
Vertical text (縦書き)Excellent
English textGood
Handwritten Japanese (手書き)Experimental

How to call

Run scripts/ocr-cli.sh from the skill root directory:

<SKILL_ROOT>/scripts/ocr-cli.sh <image_path>              # → plain text to stdout
<SKILL_ROOT>/scripts/ocr-cli.sh <image_path> --json        # → JSON with bounding boxes
<SKILL_ROOT>/scripts/ocr-cli.sh <image_path> --viz         # → also saves visualization
<SKILL_ROOT>/scripts/ocr-cli.sh <dir_path>                 # → batch all images in dir

Output formats

text (default): one line per detected text region.

json:

{
  "contents": [[
    {
      "boundingBox": [[x1,y1],[x1,y2],[x2,y1],[x2,y2]],
      "text": "recognized text",
      "confidence": 0.95,
      "isVertical": "true"
    }
  ]],
  "imginfo": { "img_width": 1920, "img_height": 1080 }
}

viz: saves viz_<filename> bounding-box overlay image to the output directory.

Performance

  • ~2-3 seconds per image on Apple Silicon (CPU)
  • Formats: JPG, PNG, TIFF, JP2, BMP
  • Charset: ~7000 characters (JIS kanji + kana + ASCII + Greek)

Tech stack

  • Layout detection: DEIMv2 (ONNX)
  • Text recognition: PARSeq cascade (30/50/100 char models, ONNX)
  • Reading order: xy-cut algorithm

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

Expedy

Expedy integration. Manage Organizations, Pipelines, Users, Filters. Use when the user wants to interact with Expedy data.

Registry SourceRecently Updated
General

Evenium

Evenium integration. Manage Events, Users, Roles. Use when the user wants to interact with Evenium data.

Registry SourceRecently Updated
General

Exhibitday

ExhibitDay integration. Manage Organizations. Use when the user wants to interact with ExhibitDay data.

Registry SourceRecently Updated
General

Enigma

Enigma integration. Manage Deals, Persons, Organizations, Leads, Projects, Activities and more. Use when the user wants to interact with Enigma data.

Registry SourceRecently Updated