Human identification and recognition system using more significant hand attributes

Hand geometry is one among the first biometrics to find practical use across an assortment of real-world security applications. A hand geometry based recognition system works by acquiring the image of a hand to determine the geometry and metrics namely the finger length, width and other attributes. Some of the existing hand geometry biometrics systems measure different parameters for efficient recognition. An important aspect of geometry based approach is the assumption that an individual’s hand does not drastically change after a certain age. Most of the existing systems use more number of attributes to describe a hand of which some like finger width may slightly vary over time. Including such attributes in the process of distance metric will notably reduce the accuracy of the system during practical implementation. So, we consider only some of the selected attributes which will not change significantly over short periods of time. Several segmentation algorithms were used in the process of extracting different kinds of features from the hand image. In this paper we present a model for hand geometry based human recognition. The paper proposes and uses some distinct features that enhance the accuracy of the recognition. In our previous work we successfully implemented a simple and very fast algorithm for hand image segmentation employing filtering, edge detection and region labeling techniques and arrived at comparable segmentation results. This technique has been employed to segment the hand images. In addition to the above, we propose the usage of some distinct features, which would enhance hand recognition much more precisely.