Recognition method after feature extraction of human vein image

Abstract

The invention discloses a recognition method after feature extraction of human vein images, which includes adopting the feature matrix template of the human vein pattern stored in the database during the registration process, and in the recognition process, first extracting the identified human body by using the same method as the registration process After obtaining the characteristic matrix of the vein pattern, after obtaining the characteristic matrix of the vein pattern, match the features of the characteristic matrix of the vein pattern with each template of the characteristic matrix of the vein pattern stored in the database, and output the matching result, which is carried out according to the following formula match: U ( P , Q ) = min ∀ h ∈ [ - m , m ] , ∀ v ∈ [ - n , n ] { Σ x = 0 M Σ y = 0 N Σ i = 1 3 ( P i ( x , y ) ⊗ Q i h , v ( x , y ) ) 3 × M × N } . The invention provides a recognition method after feature extraction of human vein images, which is simple and effective, and has a fast feature matching speed. This method of extracting features of vein images not only removes excessive redundant information, but also reduces computational complexity and amount of calculation. At the same time, it can contain more effective information. By constructing this distance function matrix to determine the effective range of the filter neighborhood, a better recognition effect can be obtained.

Description

technical field [0001] The invention relates to an identification technology for identifying the identity of a human body by distinguishing vein features, in particular to a recognition method after feature extraction of a human vein image. Background technique [0002] In the field of human identification technology, from single fingerprint identification to biometric identification, from iris technology to palm vein technology in biometric identification, everything is constantly developing and improving. In the process of image feature extraction and processing of palm veins, different extraction and processing methods bring different results, which directly affects the accuracy and singleness of identity recognition. With the research on the characteristics of human veins, it is found that not only the palm veins, but also the distribution of veins in different people have different changes. How to effectively extract the features of the extracted vein images to obtain a...

AI Technical Summary

Problems solved by technology

[0004] In the above public documents, there is no provision on how to obtain point-to-point matching of binary images through calculation, and the Gaussian filter will generate more redundant information or insufficient identification information, which increases the computational complexity and storage burden of the algorithm, and will Reduce the recognition efficiency and accuracy of the algorithm, and vein images generally have situations such as uneven global illumination, uneven texture thickness, and blurred texture boundaries that are not conducive to feature extraction. The processing of feature images is particularly important for real and effective identity authentication of different living bodies

[0005] Chinese patent application No. 200710144916.4 "Near-infrared imaging device and identification method based on palm veins and palmprints" is also based on the Gaussian matched filter to convolve the image, and the calculation formula used in the matching method is also particularly complicated. Image recognition and time occupation have a certain impact

Images