Embedded palmprint recognition system on mobile devices

There are increasing requirements for mobile personal identification, e.g. to protect identity theft in wireless applications. Based on built-in cameras of mobile devices, palmprint images may be captured and analyzed for individual authentication. However. current available palmprint recognition methods are not suitable for real-time implementations due to the limited computational resources of handheld devices, such as PDA or mobile phones. To solve this problem, in this paper, we propose a sum-difference ordinal filter to extract discriminative features of palmprint using only +/- operations on image intensities. It takes less than 200 ms for our algorithm to verify the identity of a palmprint image on a HP iPAQ PDA, about 1/10 of state-of-the-art methods' complexity, while this approach also achieves high accuracy on the PolyU palmprint database. Thanks to the efficient palmprint feature encoding scheme, we develop a real-time embedded palmprint recognition system, working on the HP PDA.