Secure Grip (TIT.6323)

Research
The main research question addressed in this proposal is whether an image of the pressure pattern exerted while holding an object can be used to reliably authenticate or identify a person. This type of biometric recognition will be called grip-pattern recognition. It will be a useful instrument to secure (1) the legal use of devices and (2) the legal access to locations. The research will focus on the design, implementation and evaluation of prototype grip-pattern recognition systems for two applications: (1) A smart gun, intended for use by the police, in which grip-pattern recognition ensures that the weapon can only be fired by its rightful user. This application will be developed in co-operation with the Dutch police (KLPD). (2) An intelligent door handle, equipped with grip-pattern recognition, capable of recognizing who enters or leaves a room. This application will be developed in co-operation with Philips Research. Both KLPD and Philips Research will provide realistic conditions of use so that the prototypes can be properly evaluated. The project involves three distinct disciplinary areas: (1) Sensors, concerning the design of pressure-sensor grids that can be applied to more or less arbitrary three-dimensional structures of various materials.
(2) Algorithms, concerning the design and implementation of biometric recognition algorithms for authentication or identification based on two-dimensional pressure patterns. (3) Security architectures, concerning aspects of, e.g., security, template management, scalability and maintenance. The sensors will be developed, using state-of-the art technology, in co-operation with Twente Solid State Technology (TSST), a company specialised in special thin-film products.
The research and engineering challenges are: (1) Development of suitable sensor arrays that can be mounted on the three-dimensional structures of the grip of the police gun and the door handle. (2) Design of recognition algorithms achieving an extremely low probability of not recognizing the rightful user from a limited set of training data. (3) Development and verification of a security architecture.

Utilization
The choice for two applications, in quite distinct domains, will lead to a broad insight in the applicability of grip-pattern recognition. Both applications are relevant to industry and end users. The operation of guns by others than the rightful user is a severe safety problem. Casualties occur among police officers who's guns are taken during a struggle. Research in the United States has shown that approximately 16% of police officers killed in the line of duty, were shot with their own guns [58]. A few approaches to solve the take-away problem have been developed, all suffering from specific drawbacks. A new and promising approach is biometric authentication of the rightful user, based on the uniqueness of body characteristics. This proposal studies the feasibility of authentication based on grip-pattern recognition in a take-away-protected gun (TAPgun), intended for use by the police. Such a gun can only be fired after successful authentication, i.e. when the measured grip pattern corresponds to information stored in the gun. Context-awareness is 'the use of context to provide task-relevant information and/or services to users, wherever they may be' [39]. It is part of the concept of ambient intelligence, of which the application in smart homes [29] is investigated at Philips Research. The intelligent door handle is capable of recognizing who enters or leaves a room. It can thus provide information about the whereabouts of the inhabitants in the home. This makes it an ideal means to contribute to context awareness in an unobtrusive, transparent way. Actual deployment of grip-pattern recognition in products depends on the results of this project. However, a regular interaction with a highly-committed user committee will increase the chance of success. In addition, the project is planned in such a way that useful results can be transferred to the user committee in an early stage. The user committee consists of:

1. Twente Solid State Technology (TSST) as a sensor manufacturer, with an interest in a market for pressure sensors. TSST offers to contribute to the development of the pressure sensors.
2. The korps landelijke politiediensten (KLPD) as an end user of the technology and capable of creating a market for the TAPgun. KLPD offers to provide 100 police officers for experiments. Weapon manufacturers
3. Carl Walther and
4. Heckler & Koch as direct users of the technology, with an interest in gun innovation.
5. Philips Research as a direct user of the technology, interested in applying grip-pattern recognition in the ambient-intelligence scenarios which are investigated in their HomeLab.
6. TNO-TPD as a research institute that studies biometrics for security and surveillance applications and is specialized in application analysis, inventory and analysis of information needs, design of system concepts, testing and evaluation of new and existing systems, and development of new functionality.

More information can be found at http://www.sas.el.utwente.nl/home/SecureGrip/.

Er zijn 7 bedrijven bij dit project betrokken.