gImageReader

A graphical interface to the Tesseract OCR engine. It loads images and PDFs from disk, a scanner, the clipboard or a screenshot, selects text areas manually or automatically and recognises them, including several pages at once. The result is saved as text, hOCR or a searchable PDF, with spell-checking. Useful for turning scanned specifications, old standards and drawings into documents you can search and copy from. Recognition quality depends on the scan quality.