Embedded Palmprint Recognition System on Mobile Devices

Abstract

Abstract. 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.

A Comparative Study on Unconstrained Hand Biometrics

“…Obviously, mobile security is not so demanding as, for instance, an application in an international airport. In the literature, there exist previous approaches concerning biometrics and mobiles involving different biometric characteristics: Face Recognition on Symbian OS [16], [17], Voice Recognition [18], Keystroke Dynamics [19], Hand [11], Palmprint [20] or Finger Pressure [18], [19], [21]. All previous work coincide on the same conclusions: mobile devices imply limitations for biometric accuracy and efficiency, but provide a high degree of security in daily applications.…”

Palmprint authentication using a symbolic representation of images

“…The applicability of using low resolution cameras equipped on PDAs or cellular phones for palmprint capturing has been studied in [20]. We implement all the four methods on an embedded platform equipped with an Intel XScale-PXA255 400 MHz embedded processor, 64 MB SDRAM and 32 MB Flash memory.…”

“…Suppose that the Palmprint ROI is 128 Â 128 pixels and the Gabor filters are 35 Â 35 in size, the overall MADD (Multiplication + Addition) operations required for one palmprint is around 120 million, leading to a very long processing time especially on slow mobile platforms. Experiments show that extracting the Competitive Code for one palmprint takes more than eight seconds on a state of the art PDA [20]. This is far too slow for a real-time biometric system.…”

[Invited Paper] Recent Advances in Biometric Recognition

“…They proposed a baseline palmprint recognition method and created a palmrpint image database * 4 . In addition, some practical systems using palmrpint recognition have been proposed such as a palmprint recognition system for mobile phones 34) and a touchless palmprint recognition system 35) . There is a good survey paper for palmprint recognition 32)36) .…”