Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Improved LDP-based human face identification method

A technology of face recognition and face recognition, which is applied in the field of face recognition based on improved LDP, can solve problems such as unsatisfactory image representation effects, and achieve fast recognition speed, good robustness, and high success rate

Inactive Publication Date: 2017-05-31
NANJING UNIV OF SCI & TECH
View PDF4 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The LBP algorithm is simple to implement and is not sensitive to consistent illumination changes, but the image representation effect of random noise and non-uniform illumination changes is not ideal

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
  • Improved LDP-based human face identification method
  • Improved LDP-based human face identification method
  • Improved LDP-based human face identification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0069] The face recognition method based on improved LDP proposed by the present invention is based on the following steps:

[0070] 1. Convert the face image to be recognized into a grayscale image of the same size;

[0071] According to the standard of general face database, all face images are adjusted to the size of 100×100.

[0072] 2. Cut the face image into sub-regions of the same size;

[0073] The face image will be cut into 4×4 sub-regions of the same size.

[0074] 3. Using the improved LDP method to extract the improved LDP eigenvalues ​​of all sub-regions cut out from the face image;

[0075] The Local Binary Pattern (LBP) algorithm takes the target pixel as the center of the circle and R as the radius, extracts P adjacent points of the target point, and then uses the pixel value of the point as the threshold, and calculates through formula (1) and formula (2) The P-bit binary code of the point:

[0076]

[0077]

[0078] here g c Represents the pixel v...

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 improved LDP-based human face identification method. The method comprises the following steps of converting a to-be-identified human face image into a grayscale image with the same size specification, and then cutting the grayscale image into sub-regions same in size; extracting improved LDP eigenvalues of all the sub-regions obtained by cutting the human face grayscale image by adopting an improved LDP method, obtaining improved LDP block images and performing block weighting by fusing structure comparison information; extracting improved LDP histogram features of the sub-regions according to weighted LDP eigenvalues of the sub-regions, and integrating the improved LDP histogram features into a whole body used for representing the human face image; performing the abovementioned processing on all human face images in a known human face library to obtain an integral improved LDP histogram feature of all human faces; extracting an improved LDP histogram eigenvector of the to-be-identified human face image, performing comparison with eigenvectors of all candidate images, calculating chi-square distances, and selecting the human face image with a minimum value as a matching human face. The method has the advantages of high calculation speed and good robustness, and increases success rate of human face identification.

Description

technical field [0001] The invention belongs to the technical field of digital image processing and pattern recognition, in particular to a face recognition method based on improved LDP. Background technique [0002] Face recognition technology refers to a technology that uses computers to detect target images, locate faces, extract effective identification information, match existing standard face databases, and obtain face identities. It has become a commonly used technology in people's work and life. One of the means of identification. The increasingly widespread and in-depth application of face recognition technology has put forward higher requirements for the ability of specific methods to solve changes in illumination, posture, and expression. Therefore, it is necessary to continue research on face recognition methods. [0003] Face recognition technology mainly includes three steps: face feature extraction, dimensionality reduction and feature classification. Genera...

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
IPC IPC(8): G06K9/00G06K9/62
CPCG06V40/161G06V40/171G06F18/2132
Inventor 王绎博沙涛
Owner NANJING UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com