gImageReader - Tesseract OCR text recognition system
gImageReader is a simple interface for tesseract-ocr. Tesseract is probably the most accurate open source optical character recognition (OCR) software available and can recognize text in over 60 languages.
It supports automatic detection of page layout, but the user can also manually define and configure recognition areas. You can import images from disk, scanning devices, clipboard and screenshots. Supports multi-page PDF documents. Recognized text is displayed directly next to the image, and basic text editing is possible, including search/replace and removing line breaks. Spell checking of output text is also supported if appropriate dictionaries are installed.
