Character Recognition by a Neural Network Using Pseudo-Zernike Moments as Input Data

スポンサーリンク

概要

• 論文の詳細を見る

• This paper describes a character recognition using pseudo-Zernike moments which are applied to a neural network. Pseudo-Zernike moments which are orthogonal complex moments are analogous to Zernike moments in process of derivation. In addition, it is possible to extract rotation inveriant features from those moments. Also pseudo-Zernike moments have strong recognition ability for the images degraded by deformation, noise, etc. The principal aim of this paper has the following two points : (1) the algorithm for the sake of increasing the recognition rate is shown and (2) the adequate range of the degree of the moments is obtained in the recognition experiments. As the results, the better outcomes by far than the ones in case of the traditional statistical classifier are obtained.

• 東海大学の論文

著者

• Kawabe Hidekazu

  Department Of Electronics

関連論文

• Rotation-invariant Digital Pattern Recognition Using Singular Value Decomposition Applied Complex-log Mapping
• Handwritten Character Recognition Using Tchebychev Moments and Pseudo-Zernike Moments
• Recognition of Rotated Images Using Complex-log Mapping
• Rotation-Invariant Character Recognition by the Moments Using Associated Legendre Functions
• Recognition of Rotated Images Using Singular Value Decomposition Applied to Complex-log Mapping
• Character Recognition by a Neural Network Using Pseudo-Zernike Moments as Input Data

スポンサーリンク