Handwriting Evaluation Using Deep Learning with SensoGrip

• DOI: 10.3390/s23115215
• Publication Date: 2023-05-31T07:21:51Z
• Authors: Mugdim Bublin; Franz Werner; Andrea Kerschbaumer; Gernot Korak; Sebastian Geyer; Lena Rettinger; Erna Schönthaler; Matthias Schmid-K...
• Keywords: Dysgraphia; Handwriting; Binary classification; Grading (engineering); Writing assessment

Handwriting learning disabilities, such as dysgraphia, have a serious negative impact on children's academic results, daily life and overall well-being. Early detection of dysgraphia facilitates an early start targeted intervention. Several studies investigated using machine algorithms with digital tablet. However, these deployed classical manual feature extraction selection well binary classification: either or no dysgraphia. In this work, we the fine grading handwriting capabilities by predicting SEMS score (between 0 12) deep learning. Our approach provided root-mean-square error less than 1 automatic instead selection. Furthermore, SensoGrip smart pen was used, i.e., equipped sensors to capture dynamics, tablet, enabling writing evaluation in more realistic scenarios.