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

Low-resolution face recognition method and apparatus

A low-resolution, face recognition technology, applied in the field of computer vision and deep learning, can solve the problems of large computing costs, restrict the actual deployment of the model, reduce the processing speed of the model, etc., and achieve the effect of good processing ability

Active Publication Date: 2018-12-21
INST OF INFORMATION ENG CAS
View PDF6 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The enhancement-based method first performs super-resolution enhanced reconstruction on the low-resolution face image, and then trains a higher-resolution model for recognition. This type of method can have a relatively good result in recognizing the reconstructed face image, but Super-resolution operations and high-resolution recognition will bring large computing costs, reduce the processing speed of the model, and restrict the actual deployment of the model

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
  • Low-resolution face recognition method and apparatus
  • Low-resolution face recognition method and apparatus
  • Low-resolution face recognition method and apparatus

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] In order to make the above solutions and beneficial effects of the present invention more comprehensible, the following will be described in detail through the examples and accompanying drawings.

[0034] The present embodiment provides a low-resolution face recognition method and a device for realizing the method, the device comprising a feature distillation module (CNN-D), a feature compression module (CNN-C) and a feature recognition module (CNN-R), The flow of the identification phase of the method is as follows figure 1 As shown in the second half, the steps include:

[0035] 1) Receive a low-resolution face image.

[0036] 2) Extract the high-dimensional depth features of low-resolution faces (ie, high-resolution face depth features) through the feature distillation module.

[0037] The feature distillation module consists of the first few layers of the student-flow deep learning network. The module receives low-resolution face images and outputs high-dimensiona...

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

A low-resolution face recognition method and apparatus Aiming at the problem of face recognition at low resolution, Especially for the low-resolution face recognition problem in natural environment, the dual-stream depth learning network structure is adopted to train the high-efficient low-resolution face recognition network by selective knowledge distillation, and the low-resolution face recognition is realized. The low-resolution face recognition network has the precision, the speed and the memory advantages close to the high-resolution face recognition model.

Description

technical field [0001] The invention belongs to the field of computer vision and deep learning, and in particular relates to a method and device for face recognition under low-resolution conditions. Background technique [0002] Human face, as a basic attribute to distinguish individuals, is frequently recognized every day in computer vision and multimedia applications. In these applications, face recognition models need to be redeployed in mobile phones or even smart cameras for camera autofocus, human-computer interaction, photo management, urban security monitoring, smart driving and many other fields. At present, in the practical application of face recognition in open environment conditions, it is often necessary to recognize low-resolution face images under the condition of extremely low computing and memory resources. In this case, many current high-precision face recognition models are often complex and difficult to deploy in practice, and when the resolution of fac...

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): G06K9/00G06K9/66G06N3/04
CPCG06V40/168G06V30/194G06N3/045
Inventor 葛仕明
Owner INST OF INFORMATION ENG CAS
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