Structural model constructing for optical handwritten character recognition

5th International Workshop on Mathematical Models and their Applications 2016

Khaustov, P.A.^1 ; Spitsyn, V.G.^1 ; Maksimova, E.I.^1

Department of Computer Engineering, Tomsk Polytechnic University, Lenin Avenue 30, Tomsk

634050, Russia^1

关键词: Character representations;    Constructing algorithms;    Hand written character recognition;    One-pass;    Processing applications;    Reference image;    Structural modeling;    Structural models;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/173/1/012006/pdf
DOI  :  10.1088/1757-899X/173/1/012006

来源: IOP

【 摘 要 】

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.