Handwriting Difficulties: A Review of Recent Advances in the Identification and Intervention
Handwriting difficulties can significantly affect education and daily functioning. Despite recent advances, challenges in standardization, dataset diversity, and model explainability still limit cross-study comparability and real-world applicability. This narrative review synthesizes recent work on...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11098793/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Handwriting difficulties can significantly affect education and daily functioning. Despite recent advances, challenges in standardization, dataset diversity, and model explainability still limit cross-study comparability and real-world applicability. This narrative review synthesizes recent work on identifying and addressing handwriting difficulties, covering both traditional and technology-based approaches. Rather than proposing a new method or computational framework, it highlights trends, challenges, and opportunities in current research. We systematically reviewed 107 primary studies published between 2019 and 2024, sourced from IEEE Xplore and SpringerLink. Key techniques examined include the use of spatiotemporal signals, image data, feature-extraction methods, and algorithmic classification. We also explored key experimental design elements and assistive interventions aimed at improving handwriting performance. Our review underscores advances in handwriting analysis—particularly the role of technology in assessing and improving handwriting legibility and fluency—and shows how these methods address limitations of conventional assessments. The findings demonstrate the potential of technology-based approaches for assessing and mitigating handwriting difficulties, while revealing ongoing challenges such as limited dataset diversity, the need to integrate cognitive and motor aspects, and inadequate model transparency. Future work should focus on standardizing methods, increasing dataset representation, and developing interpretable, multimodal solutions. |
|---|---|
| ISSN: | 2169-3536 |