Sketch2Jewelry: Semantic feature modeling for sketch-based jewelry design

Sketch-based modeling has attracted considerable attention in recent years. In this paper, we propose a semantic feature modeling system for sketch-based jewelry design, called Sketch2Jewelry. The newly devised semantic feature class encodes specific domain knowledge (jewelry design knowledge in this paper) and supplies prolific semantic information. The advantage of using semantic features is to narrow down the searching space in sketch-based feature retrieval and benefits the parameter selection from input sketches for feature instantiation and feature placement. Thus, the inaccuracy and ambiguity problems of freehand sketch inputs are alleviated within Sketch2Jewelry, compared to previous commercial feature-based modeling tools, e.g. SolidWorks, which are limited to fake sketches (i.e., not real freehand inputs). Since semantic features are high-level building blocks, together with sketch inputs, the proposed Sketch2Jewelry system can significantly improve the jewelry design efficiency. In addition, Sketch2Jewelry allows non-experts to sketch complex jewelry model naturally and efficiently with design-by-feature. Examples are provided to demonstrate its usefulness.