Gamera: A Python-based Toolkit for Structured Document Recognition

This paper presents Gamera, a newtoolkit for the creation of domain-specific structured documentrecognition applications by domain experts with limited programmingexperience. The goal of the Gamera system is to leverage the user’sknowledge of the target documents to create custom applicationsrather than attempting to meet the needs of diverse users with amonolithic application. The system allows a knowledgeable user tocombine image processing and recognition tools in an intuitive,interactive, graphical scripting environment based on Python. The useof Python in Gamera creates a simple yet powerful and flexible programming environment for novice programmers. Additionally, theresulting applications are suitable for a large-scale digitizationproject because they can be run in a batch-processing mode and easilyintegrated into a digitization framework. Finally, the Python modulesystem has been extended to allow the easy creation of plugins usingPython or C++.