DyslexiScan: A Dyslexia Detection Method from Handwriting Using CNN LSTM Model

Dyslexia is a common neurobiological learning disorder that affects millions of individuals worldwide. It is characterized by difficulty in reading and can have a significant impact on an individual's academic and professional development. Individuals with Dyslexia have trouble interpreting words and visual stimuli. While it is not a condition that can be cured, it can be effectively managed through specialized education and training. People with Dyslexia are capable of learning and being creative, but may require different teaching methods. Early recognition of dyslexia is crucial in order to provide children with the appropriate learning strategies and support they need to succeed. One potential method for detecting Dyslexia is through the analysis of handwriting patterns. DyslexiScan is a novel approach for Dyslexia Detection from Handwriting using a combination of Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) models. The CNN component is used to extract features from handwriting images, while the LSTM component is used to analyze the sequential structure of handwriting. DyslexiScan is trained on a dataset of handwriting samples from both dyslexic and non-dyslexic individuals and is evaluated using standard metrics. The results indicate that the model is capable of accurately identifying dyslexia in individuals with high accuracy, suggesting that it could be a useful tool for the early detection and intervention of Dyslexia. Additionally, this approach could be used in a clinical setting or in the education field, to help professionals to identify Dyslexia in a more efficient and accurate way.