Analyses of pupils’ polygonal shape drawing strategy with respect to handwriting performance

• Published in: Pattern analysis and applications : PAA Vol. 18; no. 3; pp. 571 - 586
• Main Authors: Tabatabaey-Mashadi, Narges, Sudirman, Rubita, Guest, Richard M., Khalid, Puspa Inayat
• Format: Journal Article
• Language: English
• Published: London Springer London 01.08.2015
• Subjects: Computer Science; Pattern Recognition; Theoretical Advances; Children’s drawing and handwriting; Support vector machine (SVM); Feature extraction
• ISSN: 1433-7541; 1433-755X
• DOI: 10.1007/s10044-014-0423-5

Polygonal shape drawing tasks are commonly used in psychological, clinical and standard handwriting tests to evaluate children’s development. Early detection of physical/mental disorders within subjects therefore requires objective analysis of the drawing tasks. This analysis would help to identify specific rehabilitation needs and accurate detection of disorders. Herein, the aim is to determine the correlation between the performance of polygonal shape drawing and levels in handwriting performance. In the reported experimentation two groups of participants aged between 6 and 7 were studied. The first group was identified by educational experts as being below-average writers within their age group whilst the second group was age-matched controls of average and above. Subjects were required to draw an isosceles triangle within a novel computer-based framework founded on a pen-based graphic tablet capture device. Subsequently, a sequential feature vector containing performance values relating to the order in which they drew the triangle was extracted from tablet data and compared against one another when presented in constructional strategy models. Statistical analyses and automated classification were applied to sequences to infer handwriting level based on the triangle drawing strategy. From our experiments drawing strategies showed significant differences in drawing end-point position, number of strokes used, and the frequency of particular drawing strategies amongst average and below-average handwriting groups. Additionally, a support vector machine classifier was used to detect group membership based on the triangle drawing strategy. From this exemplar polygonal shape drawing study it is revealed that there are details in children’s drawing strategy which considerably differs in grouping based on handwriting performance.