Related Experiment Video
Updated: Jun 29, 2026
An Objective and Child-friendly Assessment of Arm Function by Using a 3-D Sensor
Published on: February 12, 2018
Automatic assessment of fine motor development in children through hand-drawn shape images
Nai-Hsuan Hwang1, Sheng-Shan Chen1, Tun-Wen Pai2
1Department of Computer Science and Information Engineering, National Taipei University of Technology, Taipei, 10608, Taiwan.
Insights
This study introduces an automated system to assess children's fine motor skills by analyzing geometric shape drawings. The AI-powered tool accurately identifies developmental delays, aiding early intervention.
Area of Science:
- Pediatric Neurology
- Developmental Psychology
- Artificial Intelligence in Healthcare
Background:
- Fine motor skills are key indicators of neurological maturity in children.
- Current clinical assessments are resource-intensive.
- An automated, efficient system for fine motor skill evaluation is needed.
Purpose of the Study:
- To develop and validate an automated system for assessing fine motor skill development in children.
- To provide a resource-efficient alternative to traditional clinical assessments.
Main Methods:
- An AI-based system evaluated 82 children (36-72 months) drawing five geometric shapes.
- The system analyzed 23 features and assigned a maturity score.
- Performance metrics included macro F1-score (0.9236) and accuracy (0.9268).
Main Results:
- A strong positive correlation was found between fine motor skill maturity and chronological age.
- The system successfully identified children with delayed fine motor development.
- High accuracy in classifying geometric shapes indicates system reliability.
Conclusions:
- The automated system effectively assesses children's fine motor maturity using structured drawing tasks.
- The scoring system differentiates developmental stages, aiding clinical reference.
- This online tool reduces healthcare professional burden and supports early intervention.
Background:
Fine motor skills are closely related to neurological maturity among children and serve as critical indicators of developmental status. However, clinical assessments require significant human and material resources. This study proposes an automated evaluation mechanism designed to assess the development of children's fine motor skills, offering a streamlined and resource-efficient approach to developmental assessment.
Methods:
The designed system evaluated the fine motor skills of 82 children aged 36-72 months. The children were asked to replicate five geometric shapes designed by the system: circles, crosses, squares, triangles, and rhombuses. The system automatically assessed 23 distinct features across the geometric shapes using an artificial intelligence-based model. A tailored scoring system then assigned a score that reflected the child's level of fine motor skill maturity.
Results:
A total of 81 replicated drawings from the children in the test group were collected and automatically assessed using the assessment mechanism developed in this study. The results demonstrated a strong positive correlation between fine motor skill maturity and practical age. Additionally, the scores identified children with delayed fine motor development. The macro F1-score and accuracy of the automatic classification models for the five different geometric shapes in the validation dataset were 0.9236 and 0.9268, respectively. These evaluation outcomes can effectively support early intervention and treatment efforts.
Conclusion:
The system's structured drawing tasks for varying geometric shapes have substantial practical value for the automatic assessment of children's fine motor maturity. The scoring method developed in this study provides a clear distinction between the different developmental stages of children's fine motor skills. This system offers an effective online tool for assessing fine motor development among children, thereby providing essential preliminary reference information for physicians in subsequent clinical evaluations and significantly reducing the burden on healthcare professionals.
