Structural model constructing for optical handwritten character recognition

P. A. Khaustov, V. G. Spitsyn, E. I. Maksimova

Результат исследований: Материалы для журналаСтатьярецензирование


The article is devoted to the development of the algorithms for optical handwritten character recognition based on the structural models constructing. The main advantage of these algorithms is the low requirement regarding the number of reference images. The one-pass approach to a thinning of the binary character representation has been proposed. This approach is based on the joint use of Zhang-Suen and Wu-Tsai algorithms. The effectiveness of the proposed approach is confirmed by the results of the experiments. The article includes the detailed description of the structural model constructing algorithm's steps. The proposed algorithm has been implemented in character processing application and has been approved on MNIST handwriting characters database. Algorithms that could be used in case of limited reference images number were used for the comparison.

Язык оригиналаАнглийский
Номер статьи012006
ЖурналIOP Conference Series: Materials Science and Engineering
Номер выпуска1
СостояниеОпубликовано - 17 фев 2017

ASJC Scopus subject areas

  • Materials Science(all)
  • Engineering(all)

Fingerprint Подробные сведения о темах исследования «Structural model constructing for optical handwritten character recognition». Вместе они формируют уникальный семантический отпечаток (fingerprint).