On-Line Sketch Recognition Using Direction Feature
Sketch recognition is widely used in pen-based interaction, especially as the increasing popularity of devices with touch screens. It can enhance human-computer interaction by allowing a natural/free form of interaction. The main challenging problem is the variability in hand drawings. This paper presents an on-line sketch recognition method based on the direction feature. We also present two feature representations to train a classifier. We support our case by experimental results obtained from the NicIcon database. A recognition rate of 97.95% is achieved, and average runtime is 97.6ms using a Support Vector Machine classifier.
KeywordsSketched symbol recognition NicIcon database multi-stroke shapes
- 3.Ouyang, T.Y., Davis, R.: A visual approach to sketch symbol recognition. In: Proceedings of the 21st International Joint Conference on Artificial Intelligence (IJCAI 2009) (2009)Google Scholar
- 6.Eitz, M., Hays, J., Alexa, M.: How do humans sketch object? ACM Transactions on Graphics. In: Proc. SIGGRAPH (2012)Google Scholar
- 11.Niels, R., Willems, D., Vuurpijl, L.: The NicIcon database of handwritten icons. In: 11th International Conference on Frontiers in Handwriting Recognition (ICFHR 2008), Montreal, Canada, August 19-21 (2008)Google Scholar