On-Line Sketch Recognition Using Direction Feature

Abstract : 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.
Document type :
Conference papers
Paula Kotzé; Gary Marsden; Gitte Lindgaard; Janet Wesson; Marco Winckler. 14th International Conference on Human-Computer Interaction (INTERACT), Sep 2013, Cape Town, South Africa. Springer, Lecture Notes in Computer Science, LNCS-8119 (Part III), pp.259-266, 2013, Human-Computer Interaction – INTERACT 2013. 〈10.1007/978-3-642-40477-1_16〉
Liste complète des métadonnées

Cited literature [11 references]  Display  Hide  Download

https://hal.inria.fr/hal-01504888
Contributor : Hal Ifip <>
Submitted on : Monday, April 10, 2017 - 4:29:55 PM
Last modification on : Tuesday, April 11, 2017 - 8:54:59 AM
Document(s) archivé(s) le : Tuesday, July 11, 2017 - 1:54:44 PM

File

978-3-642-40477-1_16_Chapter.p...
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

Citation

Wei Deng, Lingda Wu, Ronghuan Yu, Jiazhe Lai. On-Line Sketch Recognition Using Direction Feature. Paula Kotzé; Gary Marsden; Gitte Lindgaard; Janet Wesson; Marco Winckler. 14th International Conference on Human-Computer Interaction (INTERACT), Sep 2013, Cape Town, South Africa. Springer, Lecture Notes in Computer Science, LNCS-8119 (Part III), pp.259-266, 2013, Human-Computer Interaction – INTERACT 2013. 〈10.1007/978-3-642-40477-1_16〉. 〈hal-01504888〉

Share

Metrics

Record views

141

Files downloads

19