Supercharge Your Innovation With Domain-Expert AI Agents!

Image texture feature extraction method and image recognition method

A technology of image texture and extraction method, which is applied in the field of image recognition, can solve the problems of image quality reduction and poor reliability of texture distribution characteristic values, and achieve the effects of reducing noise interference, reducing useless information extraction, and improving reliability

Pending Publication Date: 2020-10-09
GREE ELECTRIC APPLIANCES INC +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The main purpose of the present invention is to provide a method for extracting image texture features and an image recognition method to solve the problem of poor reliability of texture distribution feature values ​​extracted in the prior art, thereby reducing the quality of extracted images

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
  • Image texture feature extraction method and image recognition method
  • Image texture feature extraction method and image recognition method
  • Image texture feature extraction method and image recognition method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] In order to solve the above-mentioned technical problems existing in the prior art, an embodiment of the present invention provides a method for extracting image texture features.

[0048] figure 2 It is a flowchart of an embodiment of the method for extracting image texture features of the present invention, such as figure 2 As shown, the method for extracting image texture features in this embodiment may specifically include the following steps:

[0049] 200. Using a pre-built sliding window, intercept the target area of ​​the texture image to be recognized;

[0050] In a specific implementation process, the ROI map of the region of interest can be obtained after removing the background from the texture image to be recognized; GABOR filtering is performed on the ROI map to obtain the GABOR map. In this way, the pre-built sliding window can be used to intercept the texture image to be recognized target area, and for each target area, extract the texture features of...

Embodiment 2

[0075] Figure 4 It is a flowchart of an embodiment of the image recognition method of the present invention, such as Figure 4 As shown, the image recognition method in this embodiment may specifically include the following steps:

[0076] 400. Using the preset image texture feature extraction method, perform texture feature extraction on the texture image to be recognized and the verification image in the preset image recognition library respectively, and obtain the texture distribution feature value of the texture image to be recognized and the texture distribution of the verification image Eigenvalues;

[0077] Wherein, for the implementation process of the preset method for extracting image texture features, reference may be made to the method for extracting image texture features in the above-mentioned embodiments, which will not be repeated here.

[0078] 401. Determine the image similarity between the texture distribution feature value of the texture image to be reco...

Embodiment 3

[0082] Figure 5 It is a schematic structural diagram of an embodiment of an extraction device for image texture features of the present invention, such as Figure 5 As shown, the device for extracting image texture features in this embodiment includes an interception module 50 , a division module 51 , a comparison module 52 , a selection module 53 and a processing module 53 .

[0083] The intercepting module 50 is used to intercept the target area of ​​the texture image to be recognized by using the pre-built sliding window, and extract the texture features of the target area according to the following steps for each target area: wherein, the sliding window includes a horizontal window, a vertical window or a horizontal and vertical window Crossed cross window. The texture images to be recognized include finger vein images and / or palm vein images.

[0084] Divide module 51, be used for dividing target area into central block and surrounding blocks distributed around the cen...

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 discloses an image texture feature extraction method and an image recognition method, and the method comprises the steps: intercepting a target region of a to-be-recognized texture imagethrough a pre-built sliding window; dividing the target region into a central block and peripheral blocks distributed around the central block, and determining a pixel characteristic value of each block; comparing the pixel characteristic value of each peripheral block with the pixel characteristic value of the central block; if the textures in the target area are distributed transversely and / orlongitudinally, selecting the binary values of the peripheral blocks of the row and / or the column where the central block is located to form a binary value string representing the transverse texturesand / or the longitudinal textures; and performing data processing on the binary numerical string of the transverse texture and / or the longitudinal texture to obtain a texture distribution characteristic value of the target area, thereby realizing extraction of main information in the to-be-identified image, improving the reliability of the obtained texture distribution characteristic value, and further improving the quality of the obtained image.

Description

technical field [0001] The invention belongs to the technical field of image recognition, and in particular relates to an image texture feature extraction method and an image recognition method. Background technique [0002] With the continuous advancement of national consumption upgrades, more and more attention has been paid to the security field; texture image recognition such as finger vein recognition is currently a more prevalent biometric technology, which has the characteristics of fast recognition speed, good performance, and features that are not easy to forge. , There are more and more applications in banks, households, door gates, etc. [0003] Vein recognition systems generally use vein acquisition equipment to collect texture images, and then segment regions of interest (Region Of Interest, ROI) from the texture images, and perform GABOR filtering on ROI images to obtain GABOR images, and then perform GABOR images based on the GABOR images. The extraction of i...

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 Applications(China)
IPC IPC(8): G06K9/00
CPCG06V40/10G06V40/14
Inventor 王鹏飞李孟宸邓家璧
Owner GREE ELECTRIC APPLIANCES INC
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com