Abstract:
The article is devoted to the development of algorithms for handwritten character recognition based on constructing structural models. These algorithms do not require a large number of reference images for the correct functioning. Also, an approach to a thinning of the binary character representation based on the joint use of Zhang-Suen and Wu-Tsai algorithms has been proposed. The effectiveness of the
proposed approach is confirmed by the results of experiments.
The article includes a detailed description of all steps of the algorithm for constructing structural models. Results of the proposed algorithm's verification are provided, as well as their comparison with other character recognition algorithms. Algorithms that can operate under a limited
number of reference images were used for the comparison.
Fulltext:
PDF file (343 kB)