BIIC researchers are developing mobile biometric software that leverages standard mobile hardware, as well as innovations in sensor manufacturing that have led to the rise of the fingerprint scanning smartphones. BIIC researchers are also developing new algorithms for mobile services secured by biometric authentication for commercial as well as law enforcement.
Novel services have also been developed using cloud-based Biometric for mobile verification of faces, fingerprints, and irises. It can be applied as an enrollment and vetting solution for police, schools, public service, disaster management, health services.
Three different projects that have been accomplished by BIIC researchers on mobile
biometrics are described below:
A Cloud-Based Biometric Service Model for Iris and Ocular Recognition Using a Smartphone
This project explored research aspects related to two issues associated with cloud
- Can the cloud be used to enable biometrics matching that is much more sophisticated than what can be done locally on a smartphone?
- How can developers, particularly individuals and small companies, be incentivized to create innovative biometrics algorithms and applications?
The vision of the project, developed in consultation with the Department of Homeland Security (DHS), is for there to be a cloud service run by a neutral authority (e.g., DHS) that provides Biometrics-as-a-Service (Baas) to registered/paying users. Meanwhile, independent developers access the system via an innovative interface, making the system appear as a Platform-as-a-Service (Paas).
Developers upload their algorithms, and are credited with a micropayment each time their algorithm is used. The provider serves as a broker by automatically selecting the algorithm based on the quality of images uploaded from a user via a smartphone, the operational needs of the submitted matching request, and the economics of the micropayment scheme.
The objectives of the project were to:
- Identify the state-of-the-art in cloud computing for biometrics applications
- Develop advanced ocular-based matching algorithms that are particularly suited to the cloud yet amenable to alternative implementations
- Develop policies for encouraging innovation through micropayments and algorithms for automatic algorithm selection
- Develop and test a proof-of–concept system involving a smartphone interface for users, a virtual-machine based interface for developers, a plurality of algorithms for performing ocular matching, and a policy for selecting algorithms.
A user submits a matching request by uploading two images captured using a smartphone camera to the web interface. The comparison is performed by a worker process and a matching score, S is returned. Matching algorithm developers use the virtual machine interface to develop and submit their algorithms to the cloud infrastructure over a shell session for deployment to the worker processes.
Three-Dimensional Face Acquisition using a Smartphone
Recently, the acquisition of 3D face has gained significant interest, given the improvements in human recognition using 3D facial features. Though various 3D face scanners exist today, data acquisition using portable mobile devices still remains a critical challenge. Yet, various applications in biometrics, public safety, security, and mobile health stand to benefit from progress on this front. Our primary goal in this project is to create a hand-held portable system for the acquisition of 3D faces using a simple smartphone.
The basis of our approach is the concept of 3D shape from structured light. While the field of 3D scene analysis has been studied for decades, the technology to support the type of information needed for 3D shape from structured light only became available relatively recently. Our approach for acquiring a 3D face using a smarthphone equipped with only an RGB camera, is as follows: (1)
- we collect 3D information of the face by just illuminating it with the desired pattern and invoking algorithms for 3D reconstruction through structured light. We propose to use a small illuminant which can illuminate a scene up to 3 meters with a good contrast. It will have the form factor of a cellular phone, will be portable, and will have enough battery life to guarantee a few hours of acquisition.
- The illuminant will connect to the cellular phone, providing us the capability
to build a sophisticated structured-light system that can withstand different
variabilities in the acquisition environment. The final objective of this
project was to develop a 3D Face Acquisition System by combining a standard smartphone
with a special add-on device (illuminant) for portable acquisition of 3D faces.
The activities to accomplish this project were:
- Implementation of structured light algorithms
- Setting of the device add-on for creation of the known patterns
- Detection of the right orientation of the camera with respect to the pattern
- Interfacing the portable structured-light device with the smartphone to enable easy and flexible detection of 3D points on the face.