KimCHI: A Sketch-Based Developmental Skill Classifier to Enhance Pen-Driven Educational Interfaces for Children

Abstract

Sketching is one of the many valuable lifelong skills that children require in their overall development, and many educational psychologists manually analyze children's sketches to assess their developmental progress. The disadvantages of manual assessment are that it is time-consuming and prone to human error and bias, so intelligent sketching interfaces have strong potential in automating this process. Unfortunately, current sketch recognition techniques concentrate solely on recognizing the meaning of sketches, rather than the sketcher's developmental skill; and do not perform well on children's sketched input, as most are trained on and developed for adult's sketches. We introduce our proposed solution called KimCHI, a specialized sketch classification technique which utilizes a sketching interface for assessing the developmental skills of children from their sketches. Our approach relies on sketch feature selection to automatically classify the developmental progress of children's sketches as either developmental or mature. We evaluated our classifiers through a user study, and our classifiers were able to differentiate the users' development skill and gender with reasonable accuracy. We subsequently created an initial sketching interface utilizing our specialized classifier called EasySketch for demonstrating educational applications to assist children in developing their sketching skills.