Leap Motion Controller for authentication via hand Geometry nad Gestures Abstract:The Leap Motion controller is a consumer gesture sensor aimed to augment a user’s interactive experience with their computer. Using infrared sensors, it is able to collect data about the position and motions of a user’s hands. This data allows the Leap to be used as an authentication device. This study explores the possibility of performing both login as well as continuous authentication using the Leap Motion device. The work includes classification of static data gathered by the Leap Motion using trained classifiers, with over 99 % accuracy. In addi-tion, data was recorded from the users while utilizing the Leap Motion to read and navigate through Wikipedia pages. A template was created using the user attributes that were found to have the highest merit. The algorithm found when matching the template to the users newly col-lected data, the authentication provided an accuracy of over 98 %, and an equal error rate of 0.8 % even for a small number of attributes. This study demonstrates that the Leap Motion can indeed by used successfully to both authenticate users at login as well as while performing continu-ous activities. As the Leap Motion is an inexpensive device, this raises the potential of using its data in the future for authentication instead of traditional keyboard passwords.

1. S.S.P.M.’s College of Engineering, Kankavli
Computer Department
Leap Motion Controller for
Authentication via
Hand Geometry and Gestures
Presented by:
Mr.Omkar.G.Walavalkar
1

2. S.S.P.M.’s College of Engineering, Kankavli
Computer Department
2
INDEX
 Introduction
 Research Question
 Aims & Objectives
 Methodology & Methods
 Overview of artefact
 Results
 Conclusion
 References

3. S.S.P.M.’s College of Engineering, Kankavli
Computer Department 3
Introduction
• The Leap Motion Controller

4. S.S.P.M.’s College of Engineering, Kankavli
Computer Department 4
Research Question
Can the Leap Motion Controller be proven to be
proven to be viable user authentication device by
identifying individuals based on certain features
in their hand geometry?

5. S.S.P.M.’s College of Engineering, Kankavli
Computer Department
Aims & Objective
5
Aims:-
• Develop a data extraction application for Leap
Motion controller
• Develop custom K-NN classification method
• Process extracted data
• Obtain and analyze results and draw
conclusions

6. S.S.P.M.’s College of Engineering, Kankavli
Computer Department
Aims & Objective
6
Objectives:-
• Complete aims with:
• Microsoft Visual Studio 2013
• Microsoft Excel 2013
• Development Environment
• Windows 10 (and Later).

7. S.S.P.M.’s College of Engineering, Kankavli
Computer Department
• Spiral Lifecycle
• K-NN Identification Method
• Extract Current user’s data
• Read Data File and Populate arrays
• Compare array values and store separately
• Sort separated array
• Scoring Model Implemented
• Returned values is sorted by K-NN score
7
Methodology and Methods

8. S.S.P.M.’s College of Engineering, Kankavli
Computer Department
8
Consists of two parts:
• The First part:
• Variance of data
• Standard deviation of data
• The Second part utilizes the custom K-NN method to
determine the consistency of the leap motion.
Overview of artefact

9. S.S.P.M.’s College of Engineering, Kankavli
Computer Department
• Each finger’s:
• Metacarpal phalanges
• Proximal phalanges
• Intermediate phalanges
• Distal phalanges
• Except the thumb:
• No intermediate
9
Measurements to be collected

10. S.S.P.M.’s College of Engineering, Kankavli
Computer Department 10

11. S.S.P.M.’s College of Engineering, Kankavli
Computer Department 11
Results
• Performance metric calculations

12. S.S.P.M.’s College of Engineering, Kankavli
Computer Department 12
• Raw data analysis in Microsoft Excel

13. S.S.P.M.’s College of Engineering, Kankavli
Computer Department
13
• The FAR values indicate inconsistent and
sporadic data received from the controller .
• Variances and standard deviations support the
indication that data extracted from the Leap
Motion is highly inconsistent.
Conclusion

14. S.S.P.M.’s College of Engineering, Kankavli
Computer Department
14
1. Chan, A., Halevi, T., Memon, N.: Touchpad input for
continuous biometric authentication. In: De Decker,
B., Z´uquete, A. (eds.) CMS 2014. LNCS, vol. 8735, pp.
86–91. Springer, Heidelberg (2014)
2. Roy, A., Halevi, T., Memon, N.: An HMM-based
behavior modeling approach for continuous mobile
authentication. In: IEEE Conference on ICASSP, pp.
3789–3793 (2014)
References

15. S.S.P.M.’s College of Engineering, Kankavli
Computer Department
15
THANK YOU…