INTELLIGENT WRITING ANALYSIS SYSTEM BASED ON TOUCH TRAJECTORIES AND SPLINE FILTERING
Open Access
- 30 September 2025
- journal article
- Published by Kazakh University of Technology and Business in Вестник КазУТБ
- Vol. 3 (28)
Abstract
The article presents the development of an intelligent writing analysis system based on touch trajectories and spline filtering methods, focused on the diagnosis and development of graphomotor skills in preschoolers in digital writing learning. The relevance of the study is due to the need for early detection of difficulties in the formation of handwriting and motor coordination using objective digital tools, which is especially important when preparing children for school. Polygonal approximation, piecewise linear functions, and Catmull-Rom spline interpolation are used as the basis for mathematical analysis of trajectories. An algorithm for processing user input is proposed, which includes the stages of normalization, smoothing, comparison with a digital standard, and error categorization. The system allows you to take into account the specifics of the tool used (finger or stylus), distinguish between types of tasks (lines, continuous and discontinuous letters), as well as analyze spatial and temporal parameters of execution. As part of the testing, an experimental test of the effectiveness of the Dexterous Fingers application was conducted on a sample of 110 children aged 4-6 years. The results demonstrated a statistically significant improvement in graphomotor skills in the experimental group compared with the control group using paper records (p < 0.001). There was an increase in the proportion of children with a high level of skills, a decrease in the error rate and an increase in motivation to learn writing. The proposed system provides teachers with a tool for automated handwriting analysis, building individual development trajectories and selecting corrective tasks, and also creates the basis for further integration of artificial intelligence technologies into the processes of digital pedagogy and monitoring of children's development.Keywords
This publication has 16 references indexed in Scilit:
- Diff-ID: An Explainable Identity Difference Quantification Framework for DeepFake DetectionIEEE Transactions on Dependable and Secure Computing, 2024
- ASSESSMENT OF THE LEVEL OF FORMATION OF GRAPHOMOTOR SKILLS OF PRESCHOOL AND PRIMARY SCHOOL STUDENTS USING GRAPHIC TABLETSСовременные наукоемкие технологии (Modern High Technologies), 2024
- An Enhanced Hybrid Model Based on CNN and BiLSTM for Identifying Individuals via Handwriting AnalysisComputer Modeling in Engineering & Sciences, 2024
- Assessment of Developmental Dysgraphia Utilising a Display Tablet2023
- How Good is your Drawing? Quantifying Graphomotor Skill Using a Portable Platform2022
- Conversion Between Cubic Bezier Curves and Catmull–Rom SplinesSN Computer Science, 2021
- Identifying Learning Disability Through Digital Handwriting Analysis2021
- Handwriting in early childhood education: Current research and future implicationsJournal of Early Childhood Literacy, 2014
- Exposing Region Splicing Forgeries with Blind Local Noise EstimationInternational Journal of Computer Vision, 2013
- Geometric continuity, shape parameters, and geometric constructions for Catmull-Rom splinesACM Transactions on Graphics, 1988