De-SIGN: Robust Gesture Recognition In Conceptual Design, Sensor Analysis & Synthesis Manolya Kavakli 1 and Ali Boyali 1 VISOR (Virtual and Interactive Simulations of Reality) Research Group Department of Computing, Macquarie University Sydney NSW 2109, Australia {ali.boyali & manolya.kavakli}@mq.edu.au Summary. Designing in Virtual Reality (VR) can present new opportunities to the designers whilst improving the efficiency of the design process with the benefit of dynamically interacting with the objects in real-time using natural hand motions. Practically, the designers will be able to view the object from different angles and modify it using hand motions that they already perform when designing with traditional methods, namely pen and paper. Designing in Virtual Reality systems may bring significant advantages for the prelimi- nary exploration of the design concept in 3D. In this chapter, our purpose is to provide a design platform in VR, integrating data gloves and the sensor jacket that consists of piezo-resistive sensor threads in a sensor network. Unlike the common gesture recognition approaches, that require the assistance of expen- sive devices such as cameras or Precision Position Tracker (PPT) devices, our sensor network eliminates both the need for additional devices and the lim- itation of mobility. We developed a Gesture Recognition System (De-SIGN) in various iterations. De-SIGN decodes design gestures. In this chapter, we present the system architecture for De-SIGN, its sensor analysis and synthe- sis method (SenSe) and the Sparse Representation-based Classification (SRC) algorithm we have developed for gesture signals, and discussed the system’s performance providing the recognition rates. The gesture recognition algo- rithm presented here is highly accurate regardless of the signal acquisition method used and gives excellent results even for high dimensional signals and large gesture dictionaries. Our findings state that gestures can be recognized with over 99% accuracy rate using the Sparse Representation-based Classifi- cation (SRC) algorithm for user-independent gesture dictionaries and 100% for user-dependent.