Three-dimensional palmprint recognition method integrating multiple features and principal component analysis

Abstract

The invention provides a three-dimensional palmprint recognition method integrating multiple features and principal component analysis, which extracts geometrical features based on classification coding of shape indexes, self-adaptive correction competition coding and curved surface type feature coding, and effectively reduces the influence on the recognition rate caused by wrong distribution dueto threshold classification. Competitive coding is improved, so that the direction characteristics of the three-dimensional palmprint are expressed more accurately, block histogram statistics and principal component analysis are utilized to reduce the feature dimension and remove redundant information, so that the features are more robust to micro displacement and the discrimination is improved, Euclidean distances of the three features are used as a matching distance by weighted fusion, so that the precision and robustness of the algorithm are effectively improved, and meanwhile, a K nearestneighbor algorithm is used for realizing classification, so that the influence of abnormal values and noise in the data is effectively reduced, and the comparison time is shortened.

Description

technical field [0001] The invention belongs to the technical field of biological feature identification, and relates to a three-dimensional palmprint identification method, in particular to a three-dimensional palmprint identification method integrating multiple features and principal component analysis. Background technique [0002] In recent years, with the development of social science and technology, in application scenarios such as access control, airport and station security, banking and criminal investigation, biometric-based identification has attracted more and more attention due to its user-friendliness and reliability. As a typical member of biometrics, the palm has many characteristics that can be used for identification. Palm print refers to the "inner" epidermis layer of a person's hand, which possesses unique line features (main lines, wrinkle lines), texture features, and rich ridges and detailed feature points, and these features are considered to be unique...

AI Technical Summary

Problems solved by technology

This method is a threshold-based classification method. Since the palmprint is a non-rigid object, it is easy to produce small deformation during the measurement process and the registration of the two palmprint point clouds is not completely accurate, resulting in points near the threshold. There is bound to be a possibility of misclassification

In addition, the 3D palmprint ROI image contains a wealth of square Gabor filters to obtain the direction information of each point on the image, which is applicable in the area with obvious texture, but in the area where the texture is not obvious, the anti-competitive coding The interference ability will become very poor, and the specific performance is that the small deformation and noise of the palm will interfere with the direction judgment of the Gabor filter in the flat curvature area, resulting in misjudgment

Images