PEN-BASED GESTURE DESIGN AND RECOGNITION FOR SKETCH EDITING
Sketching is a natural and effective way for designers to express creative ideas in the phase of conceptual design. Gesture is an important interactive way to realize a certain operation for sketch editing. In this paper eight kinds of uni- stroke gestures are designed to edit conceptual sketch. A trainable gesture recognizer is presented, and various recognition algorithms are discussed in order to improve the recognition precision of gestures, such as pattern matching, support vectors machine, hidden markov model, Bayesian classifier, etc. Experiments show that the presented online sketching system can improve user adaptation and intelligence of current CAD systems.
Sketch editing Gesture Recognition Hidden Markov Model (HMM) Support Vector Machine (SVM)
GUISHENG FANG LILI HE FANSHENG KONG
School of Computer Science, Zhejiang University, Hangzhou 310027, China
国际会议
开封
英文
483-489
2006-10-15（万方平台首次上网日期，不代表论文的发表时间）