Towards Detecting Dyslexia in Children's Handwriting Using Neural Networks

Abstract: Literacy is the most reliable indicator for future success (Ritchie & Bates, 2013). Dyslexia is a learning disability that hinders a person's ability to read (Learning Disabilities Association of America). Dyslexia needs to be caught early, however, teachers are not trained to detect dyslexia (Walsh et al., 2006) and screening tests are used inconsistently. We propose (1) two new data sets of handwriting collected from children with and without dyslexia, and (2) an automated early screening technique to be used in conjunction with current approaches, to accelerate the detection process.