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

Fuzzy Face Discrimination Method Based on High Frequency Analysis of Local Neighborhood of Key Points

A technology of local neighborhood and discrimination method, applied in character and pattern recognition, computer parts, instruments, etc., can solve problems such as rare and fuzzy discrimination

Active Publication Date: 2021-06-08
TIANJIN POLYTECHNIC UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there are currently few related methods for fuzzy discrimination based on the specific characteristics of the face image itself.

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
  • Fuzzy Face Discrimination Method Based on High Frequency Analysis of Local Neighborhood of Key Points
  • Fuzzy Face Discrimination Method Based on High Frequency Analysis of Local Neighborhood of Key Points
  • Fuzzy Face Discrimination Method Based on High Frequency Analysis of Local Neighborhood of Key Points

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] Face images are a special kind of images, which are different from general images in terms of overall topology and details, and have certain unique characteristics. Therefore, the fuzzy discrimination of this type of image should not be limited to the traditional general method (especially in terms of the judgment features adopted), but should focus on the excavation and utilization of the exclusive features of face images. At the same time, due to the high degree of specialization and customization of features on this issue, it is more advantageous to use a classifier constructed through targeted training and learning to complete the work of distinguishing fuzzy faces. distinguishing mechanism. Below will carry out more specific introduction and description to the implementation method of the present invention:

[0032] Method training phase:

[0033] The key point automatic positioning model construction in the present invention and the learning module of the fuzzy ...

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 automatic analysis and discrimination method for fuzzy human face images. Compared with the existing related technical methods, this technology has strong adaptability and good robustness. It does not require manual intervention in the use phase, and is not affected by the similarity with the training face appearance. It has less dependence on training samples and takes a short time in the training phase. , making full use of the advantages of the global topology and detailed features of the face image. The main innovation of the present invention lies in the design of local neighborhood features of facial key points. Extracting the high-frequency image features of the local neighborhood at the key position of the core part of the face can not only ensure the proper application of the image detail texture that directly reflects the image clarity, but also avoid the influence of interference factors such as appearance and posture differences on the accuracy of the method. , which directly improves the robustness of the method. In addition, the present invention also introduces an integrated classifier construction strategy based on AdaBoost technology, and integrates local neighborhood fuzzy discrimination classifiers of each key point to realize integrated comprehensive intelligent decision-making.

Description

technical field [0001] The invention belongs to the fields of pattern recognition, computer vision and image processing, and relates to a fuzzy human face discrimination method centered on local features of facial key points, which can be used for intelligent discrimination of general two-dimensional human face images. Background technique [0002] With the rapid development of computer software and hardware technology and the continuous popularization of image and video acquisition equipment, intelligent image data analysis and recognition technology represented by face recognition has been more and more widely recognized and applied. However, no matter how excellent an intelligent analysis algorithm is, it must also take high-quality input information as the basic premise, and low-quality input information will inevitably directly affect the overall analysis effect of the algorithm. Therefore, it is an applied research technology with intuitive and practical significance t...

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): G06K9/00
CPCG06V40/172G06V40/171
Inventor 李月龙唐德华刘彦昌肖志涛耿磊张芳吴骏
Owner TIANJIN POLYTECHNIC UNIV
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