Iris recognition on mobile devices is a challenging task, performing acquisition via the embedded sensors can introduce the sensor interoperability problem. Biometric systems developed so far are limited in their ability of comparing biometric data originated by different sensors because they operate under the assumption that the data to be compared are obtained using the same sensor. This problem leaded to the development of biometric recognition algorithms able to work independently from the data source. In this paper, we get around the sensor interoperability problem leveraging on the picture differences due to acquisition by different sensors. We present a novel system that combines the recognition of user�s iris and user�s device, i.e. something the user is plus something the user has. To do so, we adopted an iris recognition algorithm, namely Cumulative Sums, and a well-known technique in the image forensic field for camera source identification based on the extraction of the Sensor Pattern Noise. The two identification processes are performed on the same picture leading to a system with a good trade-off between ease of use and accuracy. The approach is tested on MICHE, a database composed by iris images captured with different mobile devices in unconstrained acquisition conditions.
More detail can easily be written here using Markdown and $\rm \LaTeX$ math code.