Abstract
Structuring and rearranging free-hand sketches on large interactive surfaces typically requires making multiple stroke selections. Without well-designed selection tools, this can be both time-consuming and fatiguing. Investigating the concept of automated clustering, we conducted a background study to understand the varying perspectives of how elements in sketches can be grouped. In response to these diverse user expectations, we present cLuster, a flexible, domain-independent clustering approach for free-hand sketches. Our approach is designed to accept an initial user selection, which is then used to calculate a linear combination of pre-trained perspectives in real-time. The remaining elements are then clustered. We demonstrate the utility of our approach in a variety of application scenarios.