gImageReader
betaScreenshots
Description
A graphical GTK frontend to tesseract-ocr
gImageReader Web SiteFeatures
- Open images and PDFs
- Acquire from scanner
- Select the part of the image to recognize
- Support for different recognition languages
- Side by side comparison of source image and output text
- Remove linebreaks in output text
- Supports tesseract 3.0
User Ratings
User Reviews
-
add the thing that tesseract OCR miss: versatility
-
Works well. I case you do not know where your dictionary data resides, try /usr/share/tesseract-ocr/tessdata/
-
Good tool for everyone!
-
Nice and simple.
-
I like this project
-
Terrific software: I just upgraded to Tesseract 3.0, and was having trouble with it: it was dividing my image into columns for some reason, making a mess of the text output. I couldn't find any command-line switches to control columns. With gimageReader, the OCR just comes out right -- a single column in this case. Still don't know what switches to use, but just now I don't care -- saved my project! Thank you, Sandro. Installation on Ubuntu was a snap: downloaded gimagereader_0.9-1_all.deb and chose Open with Ubuntu Software Center. In the Software Center clicked Install, and I was done. The GUI is straightforward and efficient.