Handwriting Anomalies and Learning Disabilities through Recurrent Neural Networks and Geometric Pattern Analysis

Dyslexia and dysgraphia are learning disabilities that significantly impact reading, writing, and language processing capabilities. Dyslexia primarily affects reading, manifesting as difficulties in word recognition and phonological processing, where individuals struggle to connect sounds with corre...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-05
Main Authors: Alevizos, Vasileios, Xu, Clark, Edralin, Sabrina, Simasiku, Akebu, Malliarou, Dimitra, Zongliang Yue, Messinis, Antonis
Format: Article
Language:English
Subjects:
Anomalies
Disabilities
Disorders
Dyslexia
Feature extraction
Handwriting
Learning
Pattern analysis
Recurrent neural networks
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Dyslexia and dysgraphia are learning disabilities that significantly impact reading, writing, and language processing capabilities. Dyslexia primarily affects reading, manifesting as difficulties in word recognition and phonological processing, where individuals struggle to connect sounds with corresponding letters. Dysgraphia, on the other side, affects writing abilities, leading to problems with letter formation, spacing, and alignment. Coexistence of these disorders complicates diagnosis. This necessitates a nuanced approach that can adapt to these changes and still accurately identify and differentiate between these disorders. This study utilizes advanced geometrical patterns and recurrent neural networks (RNN) to identify handwriting anomalies indicative of dyslexia and dysgraphia. Handwriting standardized features followed by feature extraction that focuses on baseline deviations, letter connectivity, stroke thickness and other anomalies into RNN based autoencoder to identify irregularities. Initial results show the challenge associated with complex pattern adaptation.
ISSN:2331-8422