Document Processing via Trained Morphological Operators
Nina S. T. Hirata · Proceedings of the International Conference on Document Analysis and Recognition · 2007
Morphological operators have proven to be useful for many image processing tasks. However, the design of an adequate operator for a given task is not simple in general. A possible approach to deal with this difficulty is to design operators using training based methods. This work shows the application of trained morphological operators for several document processing tasks including character recognition, text segmentation and graphics processing.