A texture feature extraction method, texture feature extraction device and terminal equipment

Abstract

A texture feature extraction method provided by the present invention includes: acquiring a grayscale image, wherein the grayscale image includes palmprint information; filtering the grayscale image in N different directions by a preset filtering method, Obtain the filtered images of the grayscale images in the N different directions respectively, and perform fusion processing on the filtered images in the N different directions to obtain a first image, where N is an integer greater than 0; obtain The curvature information of each pixel in the grayscale image in M ​​different directions respectively; according to the curvature information of each pixel in the M different directions, a second image is obtained, wherein M is greater than 0. Integer; the target image is obtained by fusing the first image and the second image, and the target image includes the texture feature information in the palmprint information. Through the present invention, palmprint texture features with higher definition can be obtained.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a texture feature extraction method, a texture feature extraction device and a terminal device. Background technique [0002] Palmprints contain rich, stable and unique texture feature information, and the collection method of palmprints is relatively simple. Therefore, in technologies such as user identification, palmprint recognition has great application prospects. [0003] However, the traditional method of extracting palmprint features using adaptive thresholds has high requirements on the clarity of the palmprint image to be identified, and the accuracy of information extraction is poor. However, due to the sharpness of the image and the limitation of the method itself, it is impossible to finally obtain a high-definition and relatively complete palm print texture. SUMMARY OF THE INVENTION [0004] In view of this, embodiments of the present inventi...

AI Technical Summary

Problems solved by technology

[0003] However, the traditional method of extracting palmprint features using an adaptive threshold has high requirements on the definition of the palmprint image to be recognized, and the accuracy of information extraction is poor. Therefore, when extracting the palmprint texture, often due to the The definition of the palmprint image and the limitation of the method itself, but it is impossible to finally obtain a relatively complete palmprint texture with higher definition

Images