A statistical-topological feature combination for recognition of handwritten numerals
Applied Soft Computing
Hi-index | 0.00 |
This work concerns the analysis, implementation and evaluation of three different methods for handwritten numerical character recognition. The first approach uses a classifier based on syntactical analysis by decision tree.The other two methods consist of: (a) a conventional feed-forward Multi-layer neural network and (b) a recurrent neural network, for which the elements of the output layer are all interconnected. The CENPARMI data base was utilized for evaluation of the systems.