Explainable YOLO-Based Dyslexia Detection in Synthetic Handwriting Data

TL;DR

This paper introduces a YOLOv11-based method for detecting and classifying handwriting patterns associated with dyslexia in synthetic images, achieving near-perfect accuracy and offering a faster, more interpretable screening tool.

Contribution

The work presents a novel application of YOLO object detection to identify dyslexia-related handwriting traits in synthetic data, outperforming previous CNN-based approaches.

Findings

Achieved precision, recall, and F1 scores above 0.999

Outperformed earlier CNN and transfer-learning methods

Processed complete word images for more realistic handwriting analysis

Abstract

Dyslexia affects reading and writing skills across many languages. This work describes a new application of YOLO-based object detection to isolate and label handwriting patterns (Normal, Reversal, Corrected) within synthetic images that resemble real words. Individual letters are first collected, preprocessed into 32x32 samples, then assembled into larger synthetic 'words' to simulate realistic handwriting. Our YOLOv11 framework simultaneously localizes each letter and classifies it into one of three categories, reflecting key dyslexia traits. Empirically, we achieve near-perfect performance, with precision, recall, and F1 metrics typically exceeding 0.999. This surpasses earlier single-letter approaches that rely on conventional CNNs or transfer-learning classifiers (for example, MobileNet-based methods in Robaa et al. arXiv:2410.19821). Unlike simpler pipelines that consider each letter in isolation, our solution processes complete word images, resulting in more authentic representations of handwriting. Although relying on synthetic data raises concerns about domain gaps, these experiments highlight the promise of YOLO-based detection for faster and more interpretable dyslexia screening. Future work will expand to real-world handwriting, other languages, and deeper explainability methods to build confidence among educators, clinicians, and families.