Evaluation of Chinese Calligraphy by Using DBSC Vectorization and ICP Algorithm

Abstract

Chinese calligraphy is a charismatic ancient art form with high artistic value in Chinese culture. Virtual calligraphy learning system is a research hotspot in recent years. In such system, a judging mechanism for user’s practice result is quite important. Sometimes, user’s handwritten character is not that standard, the size and position are not fixed, and the whole character may be even askew, which brings difficulty for its evaluation. In this paper, we propose an approach by using DBSCs (disk B-spline curves) vectorization and ICP (iterative closest point) algorithm, which cannot only evaluate a calligraphic character without knowing what it is, but also deal with the above problems commendably. Firstly we find the promising candidate characters from the database according to the angular difference relations as quickly as possible. Then we check these vectorized candidates by using ICP algorithm based upon the skeleton, hence finding out the best matching character. Finally a comprehensive evaluation involving global (the whole character) and local (strokes) similarities is implemented, and a final composited evaluation score can be worked out.

A data-driven robotic Chinese calligraphy system using convolutional auto-encoder and differential evolution

“…(1) Data-driven mechanism to evaluate the quality of strokes based on the features of a collection of variations. Many existing evaluation for robotic calligraphy [10,11,12,13,14,15,16] was performed based on a diversity of the writing results due to its hard-wired mechanism. However, the proposed evaluation method applied a CAE to extract the features of stroke images from a prepared stroke image dataset.…”

“…All these methods require manual implementations to obtain fixed image patterns or stroke boundaries, which often lead to monotonous writing results. Several other projects [14,15,16] manually analyze the geometric features of calligraphy to design the evaluation methods for robotic Chinese calligraphy. One notable exception is the data-driven approach reported Chao et al [17], which introduce the Generative Adversarial Nets (GAN) to a robotic manipulator to generate writing trajectories.…”

Learning the Traditional Art of Chinese Calligraphy via Three-Dimensional Reconstruction and Assessment

“…In order to express and reflect the geometric properties of Chinese calligraphy, Sun et al [16] proposed a novel method to extract strokes using the geometric properties of the contour(s) of a character. Wang et al [17] proposed a quality assessment system for Chinese calligraphy characters based on disk B-spline curves vectorization and an iterative closest point method. In [38], Nakamura et al designed a useful tool, named beautifying font, to help Chinese calligraphy fans to learn how to write it.…”

Research on the Role of Chinese Calligraphy in the Artistic Creation

“…The current lots of outstanding design works all regard the calligraphy characters as the main design elements. For example, China bank mark is to combine coins and Chinese characters "zhong", which highlights the function of the bank, and makes the sign full of tension and heavy feeling; 2008 Olympic Games emblem is designed by the seal with quaint decoration beauty, Chinese cultural heritage for thousands of years and Olympic modern elements are perfectly combined, showing the traditional aesthetic idea of subtle, elegant, and simple [8], thus reflecting the Beijing Olympic humanistic spirit; in addition, many liquor companies logo design also use the art of calligraphy, so as to highlight the long cultural connotation of enterprise brand. "Bank of China" logo is shown in Figure 3.…”