Multispectral palmprint matching method based on tensor

Abstract

The invention discloses a multispectral palmprint matching method based on tensor, which comprises the following steps: S1, obtaining a target palmprint image; Preprocessing the interested image in the target palmprint image obtained in the step S1; S3, a feature extraction step; S2, extracting palmprint interest points on the gray level image preprocessed in the step S2; S4, a storage step; S3, storing the palmprint features extracted in the step S3 into a palmprint information base, and extracting information in the palmprint information base; S5, a feature point matching step; S4, carryingout feature point matching on the palmprint information extracted in the step S4; And S6, calculating an image matching score, constructing tensor according to the structure information between the matching point pairs, and solving the matching score to judge a matching result. According to the method, decorrelation in the color space is realized by utilizing a new algorithm, so that the contrastratio between the color spaces of all layers is higher, and meanwhile, the pictures of all layers also have richer feature information.

Description

technical field [0001] The invention relates to a tensor-based multispectral palmprint matching method, which can be used in the technical field of biological feature recognition. Background technique [0002] With the rapid development of information technology, people pay more and more attention to personal information security and public safety, so the requirements for the accuracy and real-time performance of biometric technology are also increasing. Biometric technology refers to the technology of using human physiological or behavioral characteristics to identify individuals. Common physiological characteristics include fingerprints, palmprints, retinas, faces, etc., while behavioral characteristics generally refer to handwriting and voice. Among them, due to the convenience of palmprint image collection and high user acceptance, and the feature extraction of palmprint images is relatively easy, the recognition technology of palmprint images has extremely high applicat...

AI Technical Summary

Problems solved by technology

[0003] In the field of computer vision, efficient feature recognition requires illumination estimation under complex lighting conditions. However, the correlation between color spectrum segments is high, and since most image information is represented as grayscale information, many feature extraction methods Color information is often overlooked

Images