Gamera: A Python-based Toolkit for Structured Document Recognition

This paper presents Gamera, a new toolkit for the creation of domain-specific structured document recognition applications by domain experts with limited programming experience. The goal of the Gamera system is to leverage the user’s knowledge of the target documents to create custom applications rather than attempting to meet the needs of diverse users with a monolithic application. The system allows a knowledgeable user to combine image processing and recognition tools in an intuitive, interactive, graphical scripting environment based on Python. The use of Python in Gamera creates a simple yet powerful and flexible programming environment for novice programmers. Additionally, the resulting applications are suitable for a large-scale digitization project because they can be run in a batch-processing mode and easily integrated into a digitization framework. Finally, the Python module system has been extended to allow the easy creation of plugins using Python or C++.