Scribe OCR

What Scribe OCR is

Scribe OCR recognizes text in images and helps turn scanned material into digitized documents. It places editable OCR text over the source image so users can proofread it, and can optimize a custom font for each document to improve alignment. For PDFs, it can add a searchable text layer or create text-native, ebook-style PDFs intended to represent the original. The tool imports PDF, PNG, and JPEG files, and can also use Tesseract HOCR or Abbyy XML data with character-level metrics. Popular Latin-script languages are supported; Simplified Chinese is experimental, with less accurate character positioning. An optional experimental feature exports extracted tables to XLSX. Scribe OCR runs in a browser, and its maker says data is not sent to a remote server. A local copy can be run by serving the project files over a local HTTP server, but there is no standalone desktop application. It does not directly edit PDFs: imported PDF pages are rendered as PNG images. Scribe files preserve editing sessions, but must be reopened with the original image or PDF files. It is free and open-source.