Abstract: An attempt for user adaptation in online sketch recognition is made.Two important techniques are presented：SVM-based active incremental learning for strokes classification and dynamic user modeling for composite sketchy shape recognition.Firstly,an SVM-based incremental active learning method is performed to adapt users’parameters of strokes.It can actively analyze users’incremental data and make full use of the historical data to reduce the workload of manual labeling and the training time of the classifier.Secondly,a dynamic user modeling method is adopted to build user models for each specific user in an incremental decision tree and recognize dynamically the possible shapes by means of fuzzy matching.Experiments show that the proposed method is effective and efficient.