The STUDIA UNIVERSITATIS BABE┼×-BOLYAI issue article summary

The summary of the selected article appears at the bottom of the page. In order to get back to the contents of the issue this article belongs to you have to access the link from the title. In order to see all the articles of the archive which have as author/co-author one of the authors mentioned below, you have to access the link from the author's name.

    STUDIA INFORMATICA - Issue no. Sp. Issue 1 / 2014  

  Abstract:   Due to the powerful sensors incorporated, the new generationsof smartphones have become capable of many sophisticated biometrics.Touchscreen based biometrics is a new type of biometrics showing greatpotential. In this paper we review the studies already conducted in thisdirection, then present our study aimed to nd the best method for touchdata based identi cation. We collected a large touch dataset from 71 usersusing 8 di erent mobile devices: tablets and phones. Touch data weredivided in strokes and several classi cation schemes like k-NN, RandomForests and SVM were investigated on this dataset. Measurements showthat several strokes are required for accurate user identi cation. Besidesdi erent classi cation results, statistical analysis of the collected data ispresented.

Key words and phrases. Security, Biometrics, Identi cation.

2010 Mathematics Subject Classi cation. 68T10.1998 CR Categories and Descriptors. H5.2 [Information Interfaces and Presenta-tion]: Subtopic { User Inter-faces Input devices and strategies, evaluation.
      Back to previous page