Supercharge Your Innovation With Domain-Expert AI Agents!

Back propagation (BP) neural network face recognition method based on local feature Gabor wavelets

A BP neural and local feature technology, applied in the field of face recognition, can solve the problem of large amount of calculation, achieve the effect of high recognition accuracy and reduce the amount of calculation

Inactive Publication Date: 2012-08-01
TONGJI UNIV
View PDF4 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Benefits of technology

The technical effect that this new technology solves by making it faster than previous methods while also improving its ability to recognize faces accurately without requiring too much data processing or complicated calculations.

Problems solved by technology

The technical problem addressed in this patented technology relates to improving the efficiency at recognizing faces with high accuracy while reducing processing times or computing resources required. Current methods require precise placement of eyes openings and glass lenses beforehand, making it difficult to achieve these goals simultaneously without compromising their effectiveness over long periods of operation (up to 1 hour).

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
  • Back propagation (BP) neural network face recognition method based on local feature Gabor wavelets
  • Back propagation (BP) neural network face recognition method based on local feature Gabor wavelets
  • Back propagation (BP) neural network face recognition method based on local feature Gabor wavelets

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0033] A BP neural network face recognition method based on local feature Gabor wavelet, using two-dimensional Gabor wavelet space as the feature space, using Gabor wavelet to extract feature values ​​as the input of BP neural network, and then using BP neural network for training and learning, its Gabor The model of wavelet network is as figure 1 As shown, the specific process includes as figure 2 Steps shown:

[0034] Step S1: Perform BP neural network training through each face picture in the face database to obtain a neural network classifier including a weight matrix;

[0035] Step S2: Locate the feature area of ​​the input face picture, respectively according to Figure 4 The method shown divides the eyes into 9 regions, the eyebrows into 2 regions, the nose into 4 regions, and the mouth into 6 regions. Each region selects the middle point as a feature point, and then calculates the value of each feature point Two-dimensional Gabor eigenvalues, where the Gabor kernel...

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 back propagation (BP) neural network face recognition method based on local feature Gabor wavelets, which includes the following steps: (1) performing BP neural network training through each face picture in a face database to obtain a neural network classifier containing weight matrixes; (2) performing feature area positioning on input face pictures and calculating two-dimensional Gabor feature values according to feature area position information; (3) leading the two-dimensional Gabor feature values obtained through the step (2) to generate face picture indication information; and (4) inputting the generated face picture indication information into the neural network classifier and performing face recognition according to the weight matrixes. Compared with the prior art, the BP neural network face recognition method based on local feature Gabor wavelets has the advantages of being small in operation amount, high in recognition accuracy and the like.

Description

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

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
Owner TONGJI UNIV
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