OCRFeeder is a document layout analysis and optical character recognition system.
Given the images it will automatically outline its contents, distinguish between what's graphics and text and perform OCR over the latter. It generates multiple formats being its main one ODT.
It features a complete GTK graphical user interface that allows the users to correct any unrecognized characters, defined or correct bounding boxes, set paragraph styles, clean the input images, import PDFs, save and load the project, export everything to multiple formats, etc. OCRFeeder was developed as the project of the Master's Thesis in Computer Science of Joaquim Rocha.
Where Do I Get It
Bug tracker at b.g.o:
Debian and tarball packages
Show Me The Code
You can checkout the latest sources doing the following:
git clone git://git.gnome.org/ocrfeeder
How Do I Use It
Please visit the link below to read OCRFeeder's README:
Manual in German from Ubuntu Users' wiki:
Configuration for Chinese OCR:
- Port to GObject Introspection
Add exportation to plaint text
- Add an option to exclude the graphics contents (so only text is considered when genertating a document)
- Add more options to the HTML exporation (e.g. single or multiple HTML pages)
- Add an option to use all OCR engines and automatically choose the best results
Use only one status bar instead of three
- Review the UI text to check if beginner users realize easily what the different actions do
- Review the focus events with Accerciser
- Check if an assistant-like dialog would be a good thing (this would allow converting an image into a document in X steps, kind of what the CLI does but with a graphical interface)
- --Add a UI option to choose the language of the document--
- Add support for Undo/Redo