Sketch Beautification in Air

Computer-based sketches are geometrically accurate and can be rendered formally. However, existing interfaces of sketching are complex, non-intuitive, and require considerable learning time for novice users. In our work, we aim to develop an intuitive gesture-based sketching interface that provide designers with the freedom of sketching in the air, without touching or wearing any physical device. With our novel sketching system, users could draw letters, symbols, and drawings using non-contact depth-sensing cameras, such as SoftKinetic and Leap Motion. The system records user’s hand trajectory as raw sketch. The sketch is analyzed and beautified to express user’s intent more accurately. Beautification process involves segmenting the sketch into different segments and rebuilding it to form a more beautified sketch. In this process, we use 2/3rd power law which provides novel kinematic features of segments and helps to improve beautification. Our results show encouraging performance for a broad range of writing styles and drawings in the air.

Cognitive Garment Panel Design Based on BSG Representation and Matching

Previously, the fashion industry and apparel manufacturing have been applying intelligent CAD technologies with sketching interfaces to operate garment panel shapes in digital form. The authors propose a novel bi-segment graph (BSG) representation and matching approach to facilitate the searching of panel shapes for sketch-based cognitive garment design and recommendation. First in the front-tier, they provide a sketching interface for designers to input and edit the clothing panels. A panel shape is then decomposed into a sequence of connected segments and represented by the proposed BSG model to encode its intrinsic features. A new matching metric based on minimal spanning tree is also proposed to compute the similarity between two BSG models. The simulation of the resulting garment design is also visualized and returned to the user in 3D. Experiment results show the effectiveness and efficiency of the proposed method.