GImageReader is a free OCR( optical character recognition ) utility developed by Sandro Mani, it’s a GUI frontend to Tesseract OCR. GImageReader provides you the ability to convert an image or pdf file to text with a few clicks, you can use it as an alternative to ABBYY FineReader Professional.
- It can recognize most popular languages including English, French, German, Japanese, Italian, Korean, Spanish, etc.
- Allows to recognize the entire image or only selected area of the image.
- Supported file formats include: JPEG, PNG, GIF, TIFF, PDF.
- Allows to acquire source image from digital scanners.
- Supports spell checking, you must download spell checker dictionaries from OpenOffice and extract the files to this folder: start – all programs – gImageReader – Spelling Dictionaries.
In order to get the best results, the resolution of source image should generally be between 200 dpi and 300 dpi for normal, 10-12 pt text.
For Windows users, you must download and install Tesseract and English language data for Tesseract from Code.Google.com first. After you have installed GImageReader, you should specify the “Directory containing dictionaries” to the folder of the extracted language data you downloaded from Code.Google.com.
GImageReader works on Linux and all 32 bit Windows including Windows 7 and Windows XP.