A low-resolution face recognition method

A face recognition, low-resolution technology, applied in the field of biometrics, can solve problems such as unsatisfactory face recognition, achieve the effect of improving recognition performance, strengthening classification ability, and perfect extraction

Active Publication Date: 2018-12-14
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF6 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to provide a face recognition method under low-resolution conditions to solve the problem of unsatisfactory face recognition under low-resolution conditions

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 low-resolution face recognition method
  • A low-resolution face recognition method
  • A low-resolution face recognition method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0054] The principles and features of the present invention will be described below with reference to the accompanying drawings. The examples cited are only used to explain the present invention and not used to limit the scope of the present invention.

[0055] Such as figure 1 As shown, a face recognition method under low resolution conditions includes the following steps:

[0056] S1. Obtain a low-resolution face image sample as a test sample;

[0057] S2. Extract block LTP and amplitude features from training samples in the face image sample library;

[0058] S3. Perform PCA dimensionality reduction on the block LTP and amplitude characteristics of the training samples;

[0059] S4. Train a KNN classifier through the training samples after dimensionality reduction, and classify the test samples through the KNN classifier to obtain a face recognition result.

[0060] Such as figure 2 As shown, the specific steps of step S2 are:

[0061] S21. Calculate the LTP local domain relationship...

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 low-resolution face recognition method. The invention provides a face recognition method under the condition of low resolution. By combining local ternary feature (LTP) andlocal binary amplitude (LBP-M), the histogram statistical features are extracted by blocks, and then PCA dimension reduction is carried out. The final recognition result is obtained by using KNN classifier. Through the fusion expression of various features, the extraction of low-resolution human face information is improved, the classification ability is strengthened, and the recognition performance is improved.

Description

Technical field [0001] The invention relates to the technical field of biometrics, in particular to a face recognition method under low resolution conditions. Background technique [0002] Since the 1960s, face recognition algorithms have achieved long-term development, from targeted research on a single background to the current adaptation to various complex conditions, such as expression, posture, age, occlusion, etc. Although in a constrained specific environment, the existing face recognition algorithm can achieve a better recognition rate, but the face image obtained in the real environment is often of low quality, resulting in unsatisfactory recognition performance. Face recognition in this situation is called low-resolution face recognition. [0003] Compared with the traditional high-resolution face recognition system, the face images targeted by the low-resolution face recognition system have problems such as missing information and excessive noise interference, and there...

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): G06K9/00G06K9/46G06K9/62
CPCG06V40/168G06V40/172G06V10/50G06F18/2135G06F18/24147G06F18/253
Inventor 邹见效张一凡于力徐红兵
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap