A Skeletonizing Reconfigurable Self-Organizing Model: Validation Through Text Recognition

作者：Alonso Weber J M^*; Sanchis A

来源：Neural Processing Letters, 2011, 34(1): 39-58.

DOI：10.1007/s11063-011-9182-0

• Neural networks
• Self-organizing map
• Machine printed text
• Handwritten text recognition
• Skeletonization

Self Organizing Maps are able to develop topology preserving classifiers. In this work we propose a Reconfigurable Self Organizing Model, which combines this property with others related with the generation of sub-graphs of the Delaunay-triangulation, the possibility of generating elastic approximations and the capacity to reconfigure the models topological structure in a data driven way. These properties allow us to apply the model to the extraction of linear structures from one-dimensional curves and from two-dimensional figures (which can be dense or not). Skeletonization and recognition of machine printed text and handwritten numerals serve as a validation domain.

• 出版日期2011-8