Archivists converting decades-old printed records into preservable, indexable digital text
外国語の文書をスキャンしてテキストを素早くコピー・翻訳する多言語チーム
FAQ
よくある質問
テキスト認識の精度はどのくらいですか?
精度はPDFの品質によります。明るく高解像度のテキストの場合、通常95%以上です。
OCRの精度はどのくらいですか？
Clean, well-printed text reaches up to 99% accuracy. Handwriting and low-quality scans can vary, which is why each page shows its own confidence score so you can spot pages that need a manual check.
OCR後、元のページレイアウトは保持されますか？
Yes. The OCR layer is added invisibly on top of the original image. Page layout, fonts, and positioning remain exactly as they were — only the searchability changes.
検索可能PDF、テキストPDF、.txt出力の違いは何ですか？
Searchable PDF keeps the original scanned image and adds invisible text on top so you can search and select. Text PDF generates a clean new document built only from the recognized text. The .txt option exports just the plain text with no formatting at all.
なぜファイルがアップロードされずにデバイスに留まるのですか？
The OCR engine runs entirely in your browser using WebAssembly. This means your potentially sensitive scanned documents — contracts, IDs, invoices — never leave your computer, giving you full privacy by design.