A Framework for Secure Cloud-Empowered Mobile Biometrics

In this work, we describe how computationally intensive biometric recognition can be performed on a mobile device by offloading the actual recognition process to the cloud. We focus on facial recognition, though the paradigm can be applied to other modalities. We discuss a systematic approach for dividing a recognition operation and a bulk enrollment operation into multiple tasks, which can be executed in parallel on a set of servers in the cloud, and show how the results from each task can be combined and post-processed for individual recognition or template database generation. In the context of biometrics, preserving the privacy and security of biometric data is also of paramount interest. Therefore, we further explore the role of cancelable template generation for providing privacy protection when biometric data is stored in a cloud environment.