Abstract
Since Chinese characters are composed of components, deforming the components in a small number of existing calligraphy characters to generate new characters is an effective method to produce a Chinese character library in the same style. Usually, the component deformation is achieved by affine transformation. However, when calculating the parameters in affine transformation, existing methods usually have the problems of a large amount of manual participation or complicated calculation. In this paper, we proposed an Analytic Hierarchy Process (AHP)-based Chinese character component deformation method, which is simple in calculation and can effectively realize the deformation of Chinese character components on the basis of reducing manual intervention. We first determined the factors that affect the selection of control points in affine transformation, then used AHP to calculate the weights of feature points and select the control points according to the weights. As a prerequisite for affine transformation, a matching method of Chinese character feature points based on the Chinese character skeleton map and neighborhood information is also proposed, which helps to achieve more efficient deformation. Experimental results on different fonts demonstrate the effectiveness and generality of our method.
Funder
Science and Technology Project of Hebei Education Department
Subject
Fluid Flow and Transfer Processes,Computer Science Applications,Process Chemistry and Technology,General Engineering,Instrumentation,General Materials Science
Reference28 articles.
1. Overview of Image-to-Image Translation Using Deep Neural Networks: Denoising, Super-Resolution, Modality-Conversion, and Reconstruction in Medical Imaginghttps://kyushu-u.pure.elsevier.com/ja/publications/overview-of-image-to-image-translation-by-use-of-deep-neural-netw
2. A restoration method using dual generate adversarial networks for Chinese ancient characters
3. zi2zi: Master Chinese Calligraphy with Conditional Adversarial Networkshttps://github.com/kaonashi-tyc/zi2zi/
4. Radical analysis network for learning hierarchies of Chinese characters