Palmprint Recognition Method Research

Today, with the rapid development of information and internet all over the world, information security is extraordinarily important, especially, personal identification technology. Because biological feature identification technology has unique stability, uniqueness and convenience, it is applied more and more broadly. As palmprint is typical of ease acquisition, and its major feature is apparent, stability and divisibility, palmprint automatic identification is a very potential identification technology.Through the study and research to the development history and current research to this subject, we know that this technology is still in a stage of rapid development. On the base of the main technologies in this field, we mainly focused on the palmprint location and recognition technology. In the location technology, based on the shortcomings of the existing location methods which only locate the palmprint images to finger completely open ideal situation. As for the circumstance that special shapes in fingers and that fingers closing, wiring decorations (e.g. ring), big condoyle of fingers and so on which cause the noise in the edge of finger, current methods in location can not accurately locate all the circumstances above, even fails to locate them. This paper presents a method that locates the palmprint by approximating the root of finger with line-wire from the inner part of palm. Because this method does not take advantage of the information in the edge of finger whose changes can affect the location, it can locate these circumstances above accurately. In the recognition technology, focus on the resolution of the palmprint image and the phase information of frequency. An in-depth study and analysis to the palmprint of the texture characteristics, to use gray surface identification method in the low-resolution images, the results given the identification rate and resolution of the relationship between them. When extracting the frequency information of palmprint images, phase information, This paper reviews on the frequency domain where the representatives of palmprint identification technology, and with the methods of Phase Consistency and Log-Gabor Filter Combination to extract frequency information of palmprint image, and coding it with palmprint feature codes, and to palmprint recognition. Experiments prove that it is superior to the traditional mode of using filters to determine the direction of filter method.