Contributing to Gamera
Gamera is an open source project and joining its development is always welcome. If you have written a Gamera based application or toolkit, please let us know so that we can link to it in the "Addons" section.
You are also welcome to directly contribute to the Gamera code. Here is a TODO list of possible projects. Some of these projects might nicely fit as part of a bachelor's or master's thesis. Just contact us before starting, to avoid any duplicate efforts. We are glad to provide all necessary additional information.
- More page layout analysis resp. page segmentation methods. E.g. text/graphics separation and more text line finding algorithms. Maybe some parts of Leptonica could be useful?
- Add some preprocessing operations like kfill or other local thresholding methods and multilevel thresholding.
- Feature selection via genetic algorithms (GA) as an alternative to the currently implemented GA based feature weighting.
- A new menu function in the interactive classifier dialog for highlighting outliers, i.e. possible manual misclassifications. Can be based on MNN editing.
- Add automatic clustering algorithms for training data.
- Adding more classifiers like Gaussian mixture models, support vector machines, or hidden Markov models.
- Add support for the hOCR exchange format in the form of a general writing and parsing library.
- Write wrappers for external OCR engines like Tesseract OCR as optional plugins.
- Support FFTW on Gamera images, either by porting the old Guiron Toolkit to Gamera 3.x or by passing Gamera images to and from SciPy/NumPy.
- Completely overhaul (or rewrite?) the vector toolkit. Maybe lib2geom can be utilized?
- Add more image formats: JPEG (reading/writing), PDF (writing), NIST special database 19 (reading)...