Embedded bi-modal palm biometric systemApril 29th, 2015 | Posted by in Research
Our research group has developed a novel bi-modal palm biometric system capable of touch-less capturing of two biometric parameters, palm veins and palm creases, synchronously with a single (RGB) image sensor. The developed prototype is shown in the image below.
The architecture of the proposed system is based on the Detection, Alignment and Recognition pipeline. The ROI detection and alignment stages are simplified with efficient combination of hardware (lighting sources) and software. A new feature descriptor, namely Histogram of Vectors is proposed in the recognition stage. Since the capturing of images requires special conditions, the database of 100 images of different persons was captured to evaluate the precision of the system. The analysis of performance of the system and detailed description of the system is summarized in a paper “Algorithms for a novel touchless bimodal palm biometric system” that will be published in the proceeding of International Conference on Biometrics (ICB) 2015. Full paper will soon be available for download on this webpage.
You can follow any responses to this entry through the RSS 2.0 Both comments and pings are currently closed.