A method and device for finger vein machine learning recognition based on terrain concave and convex characteristics

A technology of machine learning and recognition methods, applied in neural learning methods, character and pattern recognition, instruments, etc., can solve the difficulties of finger vein feature extraction and feature comparison technology, high efficiency optimization, and poor recognition effect of low-quality finger vein images and other issues to achieve the effect of improving the ability of identification technology and

Active Publication Date: 2022-07-05
TOP GLORY TECH INC CO LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the problem that the existing finger vein technology has poor recognition effect on low-quality finger vein images, and at the same time solve the problem that the existing finger vein feature extraction and feature comparison technology is difficult to achieve high-efficiency optimization. Finger vein machine learning recognition method and device for terrain concave-convex characteristics

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A method and device for finger vein machine learning recognition based on terrain concave and convex characteristics
  • A method and device for finger vein machine learning recognition based on terrain concave and convex characteristics
  • A method and device for finger vein machine learning recognition based on terrain concave and convex characteristics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0088] combined with figure 1 As shown in the figure, a method for identifying finger vein machine learning based on terrain concave and convex characteristics includes the following steps:

[0089] 1) Use finger vein equipment to collect registered finger vein images and verify finger vein images. The size of the collected images is 360*180. The bilinear interpolation technique is used to normalize the size of the finger vein images. The number of rows of the normalized image picH=120, the number of columns of the selected normalized image picW=60;

[0090] 2) Use bilateral filtering to perform image enhancement processing on the normalized registered finger vein images and verification finger vein images respectively, and the calculation formula is:

[0091]

[0092]

[0093] Among them, ω is the weighting coefficient of bilateral filtering, w(x, y) is the spatial kernel, is the range kernel;

[0094] In this embodiment, taking two point pixels (a, b) and (i, j) as...

Embodiment 2

[0167] refer to Figure 4 As shown, this embodiment relates to a finger vein machine learning recognition device based on terrain concavo-convex characteristics, including:

[0168] 1) Normalization processing module: used for collecting registered finger vein images and verifying finger vein images, and performing size normalization processing respectively; the normalization processing module is used to implement step 1) of Embodiment 1.

[0169] 2) Image enhancement module: used to perform image enhancement processing on the normalized registered finger vein images and verified finger vein images; the image enhancement module is used to implement step 2) of the first embodiment.

[0170] 3) Feature extraction module: used to obtain topographic concavo-convex features from the enhanced registered finger vein images and verified finger vein images, and to extract the registration features of the registered finger vein images and the verification features of the verified finger...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to a finger vein machine learning identification method and device based on terrain concave-convex characteristics. The method includes: performing size normalization processing on a registered finger vein image and a verified finger vein image; and performing image enhancement on the registered finger vein image and the verified finger vein image. Processing; based on the digital elevation model, the topographic concave and convex features are obtained from the registered finger vein images and the verified finger vein images, and the registered features and verification features are extracted; Sliding window similarity calculation is performed in the overlapping area; based on calibration correction parameters and sliding window similarity parameters, the feature extraction technical parameters and identification technical parameters of finger veins are optimized; the device includes a normalization processing module, an image enhancement module, and a feature extraction module. , parameter calculation module and optimization module. The invention improves the identification technology capability of finger veins and the adaptability to different image qualities.

Description

technical field [0001] The invention relates to the technical field of image recognition and processing, and in particular, to a method and device for machine learning recognition of finger veins based on terrain concavo-convex characteristics. Background technique [0002] Finger vein recognition technology has become one of the most promising biometric technologies due to its natural non-contact, internal features, and living body recognition. The key technologies of finger vein recognition are divided into finger vein feature extraction technology and finger vein feature comparison technology. At present, the commonly used finger vein feature extraction technologies include: finger vein skeleton line extraction technology, finger vein feature point extraction technology and finger vein binarization extraction technology. Quality finger vein images have poor adaptability. Existing finger vein feature extraction and identification technologies, such as a finger vein featu...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G06V40/12G06V10/74G06V10/82G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V40/1359G06V40/1388G06V10/245G06V10/757G06N3/045
Inventor 张烜赵国栋辛传贤李学双
Owner TOP GLORY TECH INC CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products