scholarly journals Learning to Write Stylized Chinese Characters by Reading a Handful of Examples

2018 ◽  
Author(s):  
Danyang Sun ◽  
Tongzheng Ren ◽  
Chongxuan Li ◽  
Hang Su ◽  
Jun Zhu
Keyword(s):  
Chinese Character ◽  
Optimization Method ◽  
Chinese Characters ◽  
Training Set ◽  
Generalization Ability ◽  
Complex Shapes ◽  
Character Feature

Automatically writing stylized characters is an attractive yet challenging task, especially for Chinese characters with complex shapes and structures. Most current methods are restricted to generate stylized characters already present in the training set, but required to retrain the model when generating characters of new styles. In this paper, we develop a novel framework of Style-Aware Variational Auto-Encoder (SA-VAE), which disentangles the content-relevant and style-relevant components of a Chinese character feature with a novel intercross pair-wise optimization method. In this case, our method can generate Chinese characters flexibly by reading a few examples. Experiments demonstrate that our method has a powerful one-shot/few-shot generalization ability by inferring the style representation, which is the first attempt to learn to write new-style Chinese characters by observing only one or a few examples. 

A comparison of the changes in the patterns of the usage and categorization of the classifier ‘ben 本’ in Korean, Chinese, and Japanese

2021 ◽  
Vol 5 (1) ◽  
pp. 43-51
Author(s):  
Jeong-A Jo
Keyword(s):  
Cultural Differences ◽  
Chinese Character ◽  
Chinese Characters ◽  
Common Features ◽  
The World ◽  
The Common ◽  
Korean Chinese ◽  
The Relationship

This study aims to examine the common features and differences in how the Chinese-character classifier ‘ ben 本’ is used in Chinese, Korean, and Japanese, and will explore the factors that have affected the categorization processes and patterns of the classifier ‘ ben 本.’ Consideration of the differences in the patterns of usage and categorization of the same Chinese classifier in different languages enables us to look into the perception of the world and the socio cultural differences inherent in each language, the differences in the perception of Chinese characters, and the relationship between classifiers.

A comparative study of children’s Chinese character textbooks in Korea and China, with a focus on Yu Hap

2021 ◽  
Vol 5 (2) ◽  
pp. 145-153
Author(s):  
Jeong Yeon Sil ◽  
Jang Eun Young ◽  
Park Heung Soo
Keyword(s):  
Comparative Analysis ◽  
Comparative Study ◽  
Chinese Character ◽  
Significant Proportion ◽  
Written Language ◽  
Chinese Characters ◽  
Children's Books ◽  
High Learning ◽  
Modern Chinese ◽  
Ancient Times

This study examines why and how Chinese characters spread into Korea. It subsequently conducts a comparative analysis of Korean and Chinese children’s textbooks with a focus on Yu Hap from the perspective of the acceptance and acculturation of Chinese characters. It also explores how commonly used the characters in Yu Hap are, and the text’s learning value as one of Korea’s children’s textbooks. Yu Hap is very significant as the first written language textbook published in Korea. A comparative analysis of the characters used in four children’s books published in Korea found that the characters in Yu Hap are very common, and the text has a high learning value. Approximately 50% of the characters in San Bai Qian and Yu Hap are the same, showing that both China and Korea had similar perceptions of the characters in common use. A very significant proportion of characters overlap in Basic Chinese Character for Educational Use, List of Common Words in Modern Chinese, and Yu Hap; this supports the idea that the same characters have continued to be used from ancient times to the present day.

scholarly journals Chinese Character Image Completion Using a Generative Latent Variable Model

2021 ◽  
Vol 11 (2) ◽  
pp. 624
Author(s):  
In-su Jo ◽  
Dong-bin Choi ◽  
Young B. Park
Keyword(s):  
Latent Variable ◽  
Chinese Character ◽  
Image Inpainting ◽  
Latent Variable Model ◽  
Chinese Characters ◽  
Image Completion ◽  
Variable Model ◽  
Variational Autoencoder ◽  
Convolution Model ◽  
Detection Technologies

Chinese characters in ancient books have many corrupted characters, and there are cases in which objects are mixed in the process of extracting the characters into images. To use this incomplete image as accurate data, we use image completion technology, which removes unnecessary objects and restores corrupted images. In this paper, we propose a variational autoencoder with classification (VAE-C) model. This model is characterized by using classification areas and a class activation map (CAM). Through the classification area, the data distribution is disentangled, and then the node to be adjusted is tracked using CAM. Through the latent variable, with which the determined node value is reduced, an image from which unnecessary objects have been removed is created. The VAE-C model can be utilized not only to eliminate unnecessary objects but also to restore corrupted images. By comparing the performance of removing unnecessary objects with mask regions with convolutional neural networks (Mask R-CNN), one of the prevalent object detection technologies, and also comparing the image restoration performance with the partial convolution model (PConv) and the gated convolution model (GConv), which are image inpainting technologies, our model is proven to perform excellently in terms of removing objects and restoring corrupted areas.

A research on an intelligent recognition tool for bronze inscriptions of the Shang and Zhou dynasties

2020 ◽  
Vol 4 (4) ◽  
pp. 271-279
Author(s):  
Rui Guo
Keyword(s):  
Computer Technology ◽  
Character Recognition ◽  
Chinese Character ◽  
Research Process ◽  
Chinese Characters ◽  
Chinese Character Recognition ◽  
The World ◽  
Bronze Inscriptions ◽  
Intelligent Recognition ◽  
Functional Components

The intelligent recognition tool for bronze inscriptions of the Shang and Zhou dynasties—the “Shang Zhou Bronze Inscriptions Intelligent Mirror”—was successfully invented in Shanghai. This mirror, based on the computer technology of artificial intelligence (AI) image recognition and image retrieval, succeeds in automagical recognition of bronze inscriptions, both single letters and full texts. This research leads the trend of the AI recognition of Ancient Chinese characters and accumulates valuable experience for the development of inter-disciplinary research on Chinese character recognition. This essay emphasizes the importance of the bronze inscriptions of the Shang and Zhou dynasty database in the AI recognition of bronze inscriptions, introduces the functional components of this tool, and shares the whole research process in order to offer experience for the related research on AI recognition of other types of Ancient Chinese characters as well as ideographs in the world scope. “Shang Zhou Bronze Inscriptions Intelligent Mirror” as a tool for bronze inscription recognition also has room for improvement and support, and guidance from experts in similar areas is greatly welcomed.

A comparison of the changes in the patterns of the usage and categorization of the classifier ‘ben 本’ in Korean, Chinese, and Japanese

2021 ◽  
pp. 251385022098177
Author(s):  
Jeong-A Jo
Keyword(s):  
Cultural Differences ◽  
Chinese Character ◽  
Chinese Characters ◽  
Common Features ◽  
The World ◽  
The Common ◽  
Korean Chinese ◽  
The Relationship

This study aims to examine the common features and differences in how the Chinese-character classifier ‘ ben 本’ is used in Chinese, Korean, and Japanese, and will explore the factors that have affected the categorization processes and patterns of the classifier ‘ ben 本.’ Consideration of the differences in the patterns of usage and categorization of the same Chinese classifier in different languages enables us to look into the perception of the world and the socio cultural differences inherent in each language, the differences in the perception of Chinese characters, and the relationship between classifiers.

A Feature Extracting Method for Chinese Character Recognition of License Plate Based on Elastic Mesh and Wavelet Transform

2013 ◽  
Vol 760-762 ◽  
pp. 1452-1456
Author(s):  
Chao Zheng ◽  
Hua Yang ◽  
Xing Yang ◽  
Chao Chao Huang ◽  
Xiao Di Wu
Keyword(s):  
Wavelet Transform ◽  
Character Recognition ◽  
Chinese Character ◽  
Wavelet Coefficient ◽  
Difficult Problem ◽  
License Plate ◽  
Structure Information ◽  
Feature Extracting ◽  
Chinese Character Recognition ◽  
Character Feature

Low-resolution Chinese character recognition of license plate is always a difficult problem. For solving it, we must think about the distinctiveness of character feature and the counting speed of method simultaneously. In this paper, we proposed a simple and effective feature extraction algorithm. First, extract the statistical feature of Chinese character based on decomposing stroke with wavelet transform. Second, apply Elastic Mesh Algorithm into extracting wavelet coefficient of decomposing stroke to get the structure information of Chinese character. The experimental results show the method is robust against low quality Chinese characters, such as skew, fuzzy, glue, distorted character, and easy to be used in actual projects with simple advantage.

On-Line Chinese Character Recognition Via a Representation of Spatial Relationships Between Strokes

1997 ◽  
Vol 11 (03) ◽  
pp. 329-357 ◽  
Author(s):  
Ju-Wei Chen ◽  
Suh-Yin Lee
Keyword(s):  
Character Recognition ◽  
Chinese Character ◽  
Spatial Relationship ◽  
Spatial Relations ◽  
Chinese Characters ◽  
Spatial Relationships ◽  
Matching Problem ◽  
Structural Rules ◽  
Chinese Character Recognition ◽  
On Line

Chinese characters are constructed by basic strokes based on structural rules. In handwritten characters, the shapes of the strokes may vary to some extent, but the spatial relations and geometric configurations of the strokes are usually maintained. Therefore these spatial relations and configurations could be regarded as invariant features and could be used in the recognition of handwritten Chinese characters. In this paper, we investigate the structural knowledge in Chinese characters and propose the stroke spatial relationship representation (SSRR) to describe Chinese characters. An On-Line Chinese Character Recognition (OLCCR) method using the SSRR is also presented. With SSRR, each character is processed and is represented by an attribute graph. The process of character recognition is thereby transformed into a graph matching problem. After careful analysis, the basic spatial relationship between strokes can be characterized into five classes. A bitwise representation is adopted in the design of the data structure to reduce storage requirements and to speed up character matching. The strategy of hierarchical search in the preclassification improves the recognition speed. Basically, the attribute graph model is a generalized character representation that provides a useful and convenient representation for newly added characters in an OLCCR system with automatic learning capability. The significance of the structural approach of character recognition using spatial relationships is analyzed and is proved by experiments. Realistic testing is provided to show the effectiveness of the proposed method.

The Cortical Organization of Writing Sequence: Evidence From Observing Chinese Characters in Motion

2021 ◽  
Author(s):  
Zhaoqi Zhang ◽  
Qiming Yuan ◽  
Zeping Liu ◽  
Man Zhang ◽  
Junjie Wu ◽  
...  
Keyword(s):  
Structural Equation ◽  
Chinese Character ◽  
Inferior Frontal Gyrus ◽  
Hierarchical Control ◽  
Brain Regions ◽  
Brain Network ◽  
Equation Model ◽  
Chinese Characters ◽  
General Motor ◽  
The Right

Abstract Writing sequences play an important role in handwriting of Chinese characters. However, little is known regarding the integral brain patterns and network mechanisms of processing Chinese character writing sequences. The present study decoded brain patterns during observing Chinese characters in motion by using multi-voxel pattern analysis (MVPA), meta-analytic decoding analysis, and extended unified structural equation model (euSEM). We found that perception of Chinese character writing sequence recruited brain regions not only for general motor schema processing, i.e., the right inferior frontal gyrus, shifting and inhibition functions, i.e., the right postcentral gyrus and bilateral pre-SMA/dACC, but also for sensorimotor functions specific for writing sequences. More importantly, these brain regions formed a cooperatively top-down brain network where information was transmitted from brain regions for general motor schema processing to those specific for writing sequences. These findings not only shed light on the neural mechanisms of Chinese character writing sequences, but also extend the hierarchical control model on motor schema processing.

Shape-driven control of layer height in robotic wire and arc additive manufacturing

2019 ◽  
Vol 25 (10) ◽  
pp. 1637-1646 ◽  
Author(s):  
Bohao Xu ◽  
Xiaodong Tan ◽  
Xizhi Gu ◽  
Donghong Ding ◽  
Yuelin Deng ◽  
...  
Keyword(s):  
Additive Manufacturing ◽  
Deposition Rate ◽  
Control Method ◽  
Single Layer ◽  
Optimization Method ◽  
Content Type ◽  
Layer Height ◽  
Layer Deposition ◽  
Complex Shapes ◽  
The Difference

Purpose Once an uneven substrate is aligned, traditional control theories and methods can be used on it, so aligning is of great significance for the development of wire and arc additive manufacturing (WAAM). This paper aims to propose a shape-driven control method for aligning a substrate with slopes to expand the application of WAAM. Design/methodology/approach A substrate with slopes must be aligned by depositing weld beads with slopes. First, considering the large height differences of slopes, multi-layer deposition is needed, and the number of layer of weld beads must be ascertained. Second, the change in the deposition rate is controlled as a ramp function to generate weld beads with slopes. Third, the variation of the deposition rate must be fine-tuned to compensate for the deviation between the actual and theoretical layer heights at the deposition of each layer. Finally, the parameters of the ramp functions at the deposition of each layer are determined through an optimization method. Findings First, to model the response function of layer height to deposition rate, the experiments are conducted with the deposition rate jumping from 4 to 8 mm/s and from 8 to 4 mm/s. When the deposition rate jumps from 4 to 8 mm/s and from 8 to 4 mm/s, the difference in the height of each layer decreases as the number of layer increases. Second, the variation of the deposition rate can be fine-tuned based on the deviation between the measured and theoretical layer heights because the variation of the deposition rate is proportional to the layer height when the initial and end deposition rates are near 4 or 8 mm/s, respectively. Third, the experimental results demonstrate that the proposed method is effective for single-layer aligning and aligning a substrate with one or more slopes. Originality/value The proposed method can expand the application of WAAM to an uneven substrate with slopes and lays the foundation for aligning tasks focused on uneven substrates with more complex shapes.

Sign in / Sign up

Export Citation Format

Share Document