Chinese Handwriting Research Articles

Home literacy environment mediated socioeconomic status’ impact on handwriting skill of children with intellectual disabilities

Objectives Mastering Chinese handwriting is a fundamental skill, yet it poses a challenging task for children with intellectual disability (ID). Socioeconomic status (SES) and home literacy environment (HLE) are two important family factors known to influence children’s academic achievement. This study aimed to explore the HLE’s role in SES’ influence on Chinese handwriting skill of children with ID. Methods Chinese handwriting skill was tested directly on 192 children with ID (7-12 years old), while SES and HLE questionnaires were completed by their parents. Data entry, analysis and structural equation modeling were performed using the Statistical Package for Social Sciences software. Results SES was shown not directly correlated with any of the three handwriting skills (β = 0.02, p > 0.05). Instead, the former influenced the latter indirectly via HLE; informal HLE played a complete intermediary role in this relationship (SES-informal HLE: β = 0.42, p < 0.001; informal HLE-handwriting skill: β = 0.41, p < 0.001), while formal HLE had no effect (SES-formal HLE: β = 0.34, p < 0.001; formal HLE-handwriting skill: β=-0.10, p > 0.05). Conclusions SES influences Chinese handwriting of children with ID via mediation by informal HLE. These findings emphasize the importance of maintaining high SES and creating rich HLE in the development of Chinese handwriting skill of children with ID.

Direct Retrieval of Orthographic Representations in Chinese Handwritten Production: Evidence from a Dynamic Causal Modeling Study.

This present study identified an optimal model representing the relationship between orthography and phonology in Chinese handwritten production using dynamic causal modeling, and further explored how this model was modulated by word frequency and syllable frequency. Each model contained five volumes of interest in the left hemisphere (angular gyrus [AG], inferior frontal gyrus [IFG], middle frontal gyrus [MFG], superior frontal gyrus [SFG], and supramarginal gyrus [SMG]), with the IFG as the driven input area. Results showed the superiority of a model in which both the MFG and the AG connected with the IFG, supporting the orthography autonomy hypothesis. Word frequency modulated the AG → SFG connection (information flow from the orthographic lexicon to the orthographic buffer), and syllable frequency affected the IFG → MFG connection (information transmission from the semantic system to the phonological lexicon). This study thus provides new insights into the connectivity architecture of neural substrates involved in writing.

Assessing penmanship of Chinese handwriting: a deep learning-based approach

AbstractThe rise of the digital era has led to a decline in handwriting as the primary mode of communication, resulting in negative effects on handwriting literacy, particularly in complex writing systems such as Chinese. The marginalization of handwriting has contributed to the deterioration of penmanship, defined as the ability to write aesthetically and legibly. Despite penmanship being widely acknowledged as a crucial factor in predicting language literacy, research on its evaluation remains limited, with existing assessments primarily dependent on expert subjective ratings. Recent initiatives have started to explore the application of convolutional neural networks (CNN) for automated penmanship assessment. In this study, we adopted a similar approach, developing a CNN-based automatic assessment system for penmanship in traditional Chinese handwriting. Utilizing an existing database of 39,207 accurately handwritten characters (penscripts) from 40 handwriters, we had three human raters evaluate each penscript’s penmanship on a 10-point scale and calculated an average penmanship score. We trained a CNN on 90% of the penscripts and their corresponding penmanship scores. Upon testing the CNN model on the remaining 10% of penscripts, it achieved a remarkable performance (overall 9.82% normalized Mean Absolute Percentage Error) in predicting human penmanship scores, illustrating its potential for assessing handwriters’ penmanship. To enhance accessibility, we developed a mobile application based on the CNN model, allowing users to conveniently evaluate their penmanship.

A study of ERPs acquired during handwritten and printed Chinese character processing in a lexical decision task

The aim of this study was to investigate the time course differences in brain processing between handwritten and printed Chinese characters. Behavioural and event-related potential (ERP) data were collected from twenty participants as they performed a lexical decision task in which Chinese handwritten and printed characters served as stimuli. The findings indicated that N1 reflects orthographic regularity during the early processing stage; N400 and the late positive component (LPC) data revealed that reading handwritten words evoke greater ERP amplitudes during the late processing stage. Although handwritten characters evoke greater ERP amplitudes, this did not result in more efficient behavioural outcomes. Therefore, it appears that the greater ERP amplitudes observed in the handwriting task corresponded to deeper meaning comprehension, which is also more challenging for semantic integration.

The relevance of motor sequence and visual perception skills in learning Chinese handwriting

ABSTRACT This study explored visual perception skills and the ability to write according to standard stroke order and their links to the learning of Chinese handwriting. Thirty-seven children (aged 6–8) (15 boys and 22 girls) participated in a handwriting test and visual perception evaluation (Test of Visual Perceptual Skills-3rd Edition, TVPS-3). A computerized system was used to evaluate the stroke order accuracy, legibility, and automation of stroke movements. The stroke order accuracy was found to positively correlate with the scores of TVPS-3 (r = .498, p < .05) and to significantly correlate with handwriting legibility (r = .435, p < .05) as well as the automation of stroke movements (r = .494, p < .01). This study revealed that visual perception skill is related to stroke order accuracy and provides directions to assist students who encounter difficulties in learning Chinese handwriting.

Kindergarten Visual-Perceptual and Motor Skills and Behavioral Traits Predict First-Grade Chinese Handwriting Legibility and Speed.

Clarifying the relationship between kindergarteners' characteristics and their future handwriting performance is beneficial for the early detection of children at risk of handwriting difficulties. To determine which visual-perceptual and motor skills and behavioral traits significantly predict kindergartners' Chinese handwriting legibility and speed in the first grade. One-year longitudinal, observational design. Kindergarten and elementary schools. One hundred six kindergarten children (53 boys and 53 girls; ages 5 or 6 yr) were recruited. The participants completed two subtests of the Bruininks-Oseretsky Test of Motor Proficiency-Second Edition, Test of Visual Perceptual Skills-Third Edition, Beery-Buktenica Developmental Test of Visual-Motor Integration (Beery™ VMI), and the Attention-Deficit/Hyperactivity Disorder Test-Chinese Version in kindergarten. Their handwriting legibility (character accuracy and construction) and speed were assessed by investigator-developed Chinese handwriting tests in the first grade. Multivariate regression analyses indicated the independent predictive power of spatial relationships (p = .042) and inattention (p = .004) for character accuracy. Visual-motor integration (VMI; p = .008) and inattention (p = .002) were the key predictors of character construction. Manual dexterity (p = .001) was the only significant predictor of writing speed. Kindergarteners who perform poorly in spatial relationships, VMI, manual dexterity, and attention are likely to have less legible Chinese handwriting and slow writing speed in first grade. Plain-Language Summary: Children's visual-perceptual and motor skills and behavioral traits in kindergarten can predict their Chinese handwriting legibility and speed in first grade. This study found that kindergarteners who performed poorly in spatial relationships, VMI, manual dexterity, and attention were likely to have less legible Chinese handwriting and slow writing speed in the first grade.

MobileNetV3-based Handwritten Chinese Recognition Towards the Effectiveness of Learning Hanzi

Writing Mandarin characters is considered the most challenging component for beginners due to the rules and character formations. This paper explores the potential of a machine learning-based digital learning tool for writing Mandarin characters. It also conducts a comparative study between MobileNetV2 and MobileNetV3, exploring different configurations. The research follows the Multimedia Development Life Cycle (MDLC) method to create both the application and machine learning models. Participants from higher education institutions that offer Mandarin courses in Batam, Indonesia, were involved in a User Acceptance Test (UAT). Data was gathered through questionnaires and analyzed using the System Usability Scale (SUS) methods. The results show positive user acceptance, with an SUS score of 77.92%, indicating a high level of acceptability. MobileNetV3Small was also preferred for recognizing the user’s handwriting, due to comparable accuracy size, rapid inference time, and smallest model size. While the application was well-received, several participants provided constructive feedback, suggesting potential improvements.

DYPA

Identifying early a person with dyslexia, a learning disorder with reading and writing, is critical for effective treatment. As accredited specialists for clinical diagnosis of dyslexia are costly and undersupplied, we research and develop a computer-assisted approach to efficiently prescreen dyslexic Chinese children so that timely resources can be channelled to those at higher risk. Previous works in this area are mostly for English and other alphabetic languages, tailored narrowly for the reading disorder, or require costly specialized equipment. To overcome that, we present DYPA, a novel DYslexia Prescreening mobile Application for Chinese children. DYPA collects multimodal data from children through a set of specially designed interactive reading and writing tests in Chinese, and comprehensively analyzes their cognitive-linguistic skills with machine learning. To better account for the dyslexia-associated features in handwritten characters, DYPA employs a deep learning based multilevel Chinese handwriting analysis framework to extract features across the stroke, radical and character levels. We have implemented and installed DYPA in tablets, and our extensive trials with more than 200 pupils in Hong Kong validate its high predictive accuracy (81.14%), sensitivity (74.27%) and specificity (82.71%).

Reliability, validity, and measurement invariance of a Chinese handwriting legibility scale among primary students in central China.

Chinese handwriting has a close relationship with spatial cognition, and the legibility dimension is prominent with its spatial-oriented characteristics. However, handwriting evaluation focusing on the detailed spatial aspects of the legibility dimension in the Chinese context is rare. We aimed to develop a Chinese Handwriting Legibility Scale (CHLS) and examine its reliability, validity, and measurement invariance among Chinese primary students of different grades. A total of 684 students aged 8-12 years were recruited from a mainstream primary school in central China and were asked to copy a Chinese template as legibly as possible within 4 min. The developed CHLS was used to assess these students' legibility performance. The seven-criteria CHLS favored content validity. The inter-rater reliability was good; however, the scoring instructions need to be refined. Principal component analysis (PCA) revealed a one-factor solution explaining 62.336% of the variance of the seven-criteria CHLS, and confirmatory factor analysis (CFA) confirmed its appropriateness. There was a high internal consistency (α = 0.902). In terms of measurement invariance, the factor structures and loadings of the CHLS were consistent across students of different grades; however, significant intercept variations were detected between students of Grades 2 and 4. CHLS may be effective for evaluating Chinese handwriting legibility performance in the Chinese primary school context in the central region. Students' Chinese handwriting legibility performance may have developmental specificity in different grades.

Offline Handwritten Chinese Character Using Convolutional Neural Network: State-of-the-Art Methods

Given the presence of handwritten documents in human transactions, including email sorting, bank checks, and automating procedures, handwritten characters recognition (HCR) of documents has been invaluable to society. Handwritten Chinese characters (HCC) can be divided into offline and online categories. Online HCC recognition (HCCR) involves the trajectory movement of the pen tip for expressing linguistic content. In contrast, offline HCCR involves analyzing and categorizing the sample binary or grayscale images of characters. As recognition technology develops, academics’ interest in Chinese character recognition has continuously increased, as it significantly affects social and economic development. Recent development in this area is promising. However, the recognition accuracy of offline HCCR is still a sophisticated challenge owing to their complexity and variety of writing styles. With the advancement of deep learning, convolutional neural network (CNN)-based algorithms have demonstrated distinct benefits in offline HCCR and have achieved outstanding results. In this review, we aim to show the different HCCR methods for tackling the complexity and variability of offline HCC writing styles. This paper also reviews different activation functions used in offline HCCR and provides valuable assistance to new researchers in offline Chinese handwriting recognition by providing a succinct study of various methods for recognizing offline HCC.

Handwriting on Touch Screens through Fingers and Stylus: Investigating the Optimal Size of the Input Box for Younger and Older Adults

Handwriting is widely used by Chinese older adults for text input on touch screens, but their handwriting performance is relatively low in comparison to younger adults. Therefore, this study investigated how the size of the input box (15%, 30%, and 45% of the display), input method (fingers and stylus), display size (4.7 inches and 7.9 inches), and age (younger adults and older adults) influence Chinese handwriting performance and user experience. An experiment was conducted among 72 participants. A system was developed to automatically record the time of handwriting, the accuracy of handwriting, the number of protruding strokes, the number of rewritings. Besides, participants’ satisfaction, preferences, and mental workload were measured through questionnaires. The results revealed significant effects of the size of the input box, age, input method, and display size on the performance indexes and subjective ratings. Accordingly, 12 design implications for improving the Chinese handwriting system were identified.

The Challenges of Recognizing Offline Handwritten Chinese: A Technical Review

Offline handwritten Chinese recognition is an important research area of pattern recognition, including offline handwritten Chinese character recognition (offline HCCR) and offline handwritten Chinese text recognition (offline HCTR), which are closely related to daily life. With new deep learning techniques and the combination with other domain knowledge, offline handwritten Chinese recognition has gained breakthroughs in methods and performance in recent years. However, there have yet to be articles that provide a technical review of this field since 2016. In light of this, this paper reviews the research progress and challenges of offline handwritten Chinese recognition based on traditional techniques, deep learning methods, methods combining deep learning with traditional techniques, and knowledge from other areas from 2016 to 2022. Firstly, it introduces the research background and status of handwritten Chinese recognition, standard datasets, and evaluation metrics. Secondly, a comprehensive summary and analysis of offline HCCR and offline HCTR approaches during the last seven years is provided, along with an explanation of their concepts, specifics, and performances. Finally, the main research problems in this field over the past few years are presented. The challenges still exist in offline handwritten Chinese recognition are discussed, aiming to inspire future research work.

HUTNet: An Efficient Convolutional Neural Network for Handwritten Uchen Tibetan Character Recognition.

Recognition of handwritten Uchen Tibetan characters input has been considered an efficient way of acquiring mass data in the digital era. However, it still faces considerable challenges due to seriously touching letters and various morphological features of identical characters. Thus, deeper neural networks are required to achieve decent recognition accuracy, making an efficient, lightweight model design important to balance the inevitable trade-off between accuracy and latency. To reduce the learnable parameters of the network as much as possible and maintain acceptable accuracy, we introduce an efficient model named HUTNet based on the internal relationship between floating-point operations per second (FLOPs) and Memory Access Cost. The proposed network achieves a ResNet-18-level accuracy of 96.86%, with only a tenth of the parameters. The subsequent pruning and knowledge distillation strategies were applied to further reduce the inference latency of the model. Experiments on the test set (Handwritten Uchen Tibetan Data set by Wang [HUTDW]) containing 562 classes of 42,068 samples show that the compressed model achieves a 96.83% accuracy while maintaining lower FLOPs and fewer parameters. To verify the effectiveness of HUTNet, we tested it on the Chinese Handwriting Data sets Handwriting Database 1.1 (HWDB1.1), in which HUTNet achieved an accuracy of 97.24%, higher than that of ResNet-18 and ResNet-34. In general, we conduct extensive experiments on resource and accuracy trade-offs and show a stronger performance compared with other famous models on HUTDW and HWDB1.1. It also unlocks the critical bottleneck for handwritten Uchen Tibetan recognition on low-power computing devices.

Development and Psychometric Evaluation of the Computer-Aided Measure of Chinese Handwriting Legibility (CAM-CHL) for School-Age Children

Handwriting legibility is the main criterion for determining whether a child has handwriting difficulties. A comprehensive assessment of handwriting legibility with sound psychometrics is essential to timely identification of handwriting difficulties and outcome measurement after handwriting interventions. To evaluate the psychometrics of the Computer-Aided Measure of Chinese Handwriting Legibility (CAM-CHL) and to investigate Chinese handwriting legibility in school-age children using the CAM-CHL. Cross-sectional, repeated observation, test-retest. Elementary schools in Taiwan. We recruited 25 lower-grade children for the examination of test-retest reliability, 75 children from all grade levels, and 10 senior schoolteachers for the examination of the CAM-CHL's convergent validity and the investigation of handwriting legibility. Children were asked to copy a set of Chinese characters as legibly as possible. We used the CAM-CHL to assess handwriting legibility in four domains: Size, Orientation, Position, and Deformation. The schoolteachers were asked to subjectively assess the handwriting legibility using a 3-point Likert-type scale. The CAM-CHL demonstrated good to excellent test-retest reliability and acceptable random measurement error in all legibility domains. The CAM-CHL had fair to moderate convergent validity with schoolteachers' perceptions. Additionally, upper-grade children had better handwriting legibility in the Size and Position domains than lower-grade children. The CAM-CHL, a comprehensive and objective method of assessing Chinese handwriting legibility, has sound reliability and acceptable validity, suggesting its potential as an outcome measure for school-age children. What This Article Adds: The CAM-CHL can be used in comprehensive evaluations of Chinese handwriting legibility in school-age children. The CAM-CHL has acceptable psychometrics for use as an outcome measure.

Brain Correlates of Chinese Handwriting and Their Relation to Reading Development in Children: An fMRI Study.

Handwriting plays an important role in written communication, reading, and academic success. However, little is known about the neural correlates of handwriting in children. Using functional magnetic resonance imaging (fMRI) and a copying task, we investigated regional brain activation and functional lateralization associated with Chinese handwriting in children (N = 36, 9-11 years old), as well as their relations to reading skills. We found significant activation of the bilateral frontal motor cortices, somatosensory cortex, intraparietal sulcus (IPS), fusiform gyrus (FuG), and cerebellum during handwriting, suggesting that an adult-like brain activation pattern emerges by middle childhood. Moreover, children showed left-lateralized and bilateral activation of motor regions and right-lateralized activation of the FuG and cerebellum during handwriting, suggesting that functional lateralization of handwriting is not fully established by this age. Finally, the activation of Exner's area and the lateralization of the IPS and cerebellum during handwriting were correlated with reading skills, possibly representing a neural link between handwriting and reading in children. Collectively, this study reveals the brain correlates of handwriting and their relation to reading development in Chinese children, offering new insight into the development of handwriting and reading skills.

Chinese handwriting while driving: Effects of handwritten box size on in-vehicle information systems usability and driver distraction

Objective Handwritten box size (HBS) is an essential Chinese handwriting interface element when interacting with touchscreen-based in-vehicle information systems (IVISs) since it is compactly bound up with driver distraction besides usability issues. Miscellaneous HBSs are commercially available on IVISs, yet the details of how the drivers interact with them in an in-vehicle display situation remain sparsely examined. Therefore, this study set out to investigate the effects of HBS on IVISs usability (task completion time, number of errors, number of protruding strokes, and NASA-TLX, a subjective workload assessment tool) and driver distraction (mean speed, lane position variation, total glance time, number of glances, mean glance time, and number of glances exceeding 1.6 s). Ultimately, the appropriate HBS on IVISs is determined. Methods A simulated driving experiment involving thirty drivers was launched. The primary task was lane-keeping with speed ranging from 40 to 60 km/h, and the secondary task was entering a 5-character text by Chinese handwriting input under five different HBS conditions: 25 × 25 mm, 30 × 30 mm, 35 × 35 mm, 40 × 40 mm, and 45 × 45 mm. A battery of one-way repeated measure analyses of variance (r-ANOVA) was used to examine which HBS can maximize IVISs usability and minimize driver distraction with the smallest HBS. Results Generally, the issues of IVISs usability and driver distraction improved progressively as the HBS increased to a specific size (40 × 40 mm in this study), at which they got to the asymptotes. Specifically, HBS below 40 × 40 mm was associated with longer text input time, more errors and protruding strokes, extended eyes-off-road time, excessive off-road glances, and deteriorative lateral driving performance. Nevertheless, there were no significant differences in mean glance time and longitudinal driving performance. No improvement measures were observed for HBS above 40 × 40 mm, except for a higher perceived workload. Conclusions Overall, the appropriate HBS of in-vehicle Chinese handwriting was found to be 40 × 40 mm. Considering that the in-vehicle human-machine interface (HMI) has limited display space and increasing visual complexity, these findings may help develop evidence-based design guidelines for driver-friendly IVISs and prevent distracted-related traffic injuries.

Role of radical position and character configuration in Chinese handwritten production

Role of radical position and character configuration in Chinese handwritten production

Functional brain networks underlying the interaction between central and peripheral processes involved in Chinese handwriting in children and adults.

The neural mechanisms that support handwriting, an important mode of human communication, are thought to be controlled by a central process (responsible for spelling) and a peripheral process (responsible for motor output). However, the relationship between central and peripheral processes has been debated. Using functional magnetic resonance imaging, this study examined the neural mechanisms underlying this relationship in Chinese handwriting in 36 children (mean age=10.40 years) and 56 adults (mean age=22.36 years) by manipulating character frequency (a central variable). Brain network analysis showed that character frequency reconfigured functional brain networks known to underlie motor processes, including the somatomotor and cerebellar network, in both children and adults, indicating that central processing cascades into peripheral processing. Furthermore, the network analysis characterized the interaction profiles between motor networks and linguistic-cognitive networks, fully mapping the neural architecture that supports the interaction of central and peripheral processes involved in handwriting. Taken together, these results reveal the neural interface underlying the interaction between central and peripheral processes involved in handwriting in a logographic writing system, advancing our understanding of the neural basis of handwriting.

On Image-Processing-Based Identification Method of Express Logistics Information

As a modern comprehensive information platform for integrated statistical analysis of express shipments information and for express shipments management decision-making, the express logistics track and trace system needs to use artificial intelligence (AI) technology and image processing technology to automatically extract the text content of express logistics documents. Existing express shipments information identification models usually have problems such as less-than-ideal performance in detecting single characters or small text regions of express logistics documents, high human resource cost for character-level markup, and low speed and accuracy of text recognition. In response, this paper studies the image-processing-based identification method of express logistics information. It presents a recognition process for pre-processing text images of express logistics documents, along with a detailed description of denoising, greyscaling and binarisation methods. While proposing an enhancement strategy for Chinese characters in the section of handwritten Chinese, this paper constructs a model for recognition of express shipping document texts based on bidirectional long-short term memory (LSTM) and attention mechanism. In this way, we fully mined key semantic information of express logistics document texts. The experimental results verify the effectiveness of the constructed model.

Exploring Orthographic Representation in Chinese Handwriting: A Mega-Study Based on a Pedagogical Corpus of CFL Learners.

Writing and reading are closely related and are thus likely to have a common orthographic representation. A fundamental question in the literature on the production of written Chinese characters concerns the structure of orthographic representations. We report on a Chinese character handwriting pedagogical corpus involving a class of 22 persons, 232 composite character types, 1,913 tokens, and 13,057 stroke records, together with the inter-stroke interval (ISI), which reflects the parallel processing of multilevel orthographic representation during the writing execution, and 50 orthographic variables from the whole character, logographeme, and stroke. The results of regression analyses show that orthographic representation has a hierarchy and that different representational levels are active simultaneously. In the multilevel structure of orthographic representation, the representation of the logographeme is absolutely dominant. Writing and reading have both commonalities and individual differences in their orthographic representations. The online processing of the logographeme unit probably occurs at the ISI before the initial stroke of the current logographeme, which may also cascade to the first subsequent logographeme. In addition, we propose a new effective character structure unit for describing orthographic complexity.