3D palm print identification method

Abstract

The invention discloses a 3D palm print identification method, comprising steps of performing pre-processing on the 3D palm print and turning the palm print into a one-dimension image, calculating a correlation coefficient of an inter-class image pair and an intra-class image pair as a new sample, using a new sample to train a stacking type noise reduction automatic coding machine to extract a new sample characteristic and obtain a trained noise reduction automatic coding machine, training a plurality of weak classifiers on the basis of the real adaboost algorithm and a new sample characteristic extracted from the previous step, combining the weak classifiers into a strong classifier, inputting a new 3D palm print image by a user, and comparing the newly-inputted 3D palm print image of the user with the 3D palm print image which is preset in the sample database to determine whether the 3D palm print image is the same or the foreign. The 3D palm print identification method is simple and fast in realization, adopts the coherent algorithm to calculate the consistency between the images, determines whether the images are the data samples of the same user, solves the displacement problem of the small palm print image and the difficulty that the registering algorithm needs to find the positioning information, and has a good robustness.

Description

technical field [0001] The invention relates to palmprint recognition technology, in particular to a 3D palmprint authentication method. Background technique [0002] Palmprint recognition is an important biometric technology. The palmprint image contains rich line features and texture features, which makes it of high application value in identity authentication. However, there are some problems in the traditional 2D palmprint recognition technology that are difficult to solve properly: (1) 2D palmprint is easily disturbed by factors such as light changes and skin surface smears. (2) Changes in image features caused by finger gesture changes. (3) The existing feature extraction methods are difficult to make full use of the useful information in the image. Recently, Zhang Dapeng of the Hong Kong Polytechnic University and others proposed a three-dimensional palmprint recognition technology, which can effectively overcome the interference of light changes, but the other two ...

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide a new 3D palmprint authentication method to solve the problem that the current existing methods are difficult to make full use of the useful information in the palmprint image for palmprint authentication and identification

Images