Motion invariant palm-print texture based biometric security

AbstractBiometric based identification is an emerging technology that can solve many security problems. Although systems based on fingerprint and eye features have so far achieved the best matching performance, human hand also contains a wide variety of features, e.g. shape, texture and principal palm lines etc. This feature of the human hand is quite stable and hand images can be extracted very easily. Palm-print is a new and emerging biometric feature for personal recognition. This paper describes an automated approach to palm-print recognition. In contrast to existing palm-print based biometric systems, a new system which is resistant to motion variance of the palm has been proposed. A Palm-print image is taken as an input and then a low pass Gaussian filter is applied to remove the noise from image. Further, since the centre of mass always remains constant, so this property has been taken into account to extract the ROI (Region of Interest) from palm-print image. SIFT (Scale Invariant Feature Transformation) features have been used further for extracting stable texture features from the ROI and are stored. These stable features extracted from the ROI are further used for comparison with stable texture features extracted from ROI of other palmprint images to provide biometric based identification and security