Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Feb 25, 2026

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

10.1K

A novel deep learning algorithm for incomplete face recognition: Low-rank-recovery network.

Jianwei Zhao1, Yongbiao Lv1, Zhenghua Zhou1

  • 1Department of Mathematics and Information Sciences, China Jiliang University, Hangzhou 310018, Zhejiang Province, PR China.

Neural Networks : the Official Journal of the International Neural Network Society
|August 4, 2017
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Bacteroides acidifaciens attenuates Concanavalin A-induced liver injury by remodeling bile acids to suppress CD95-mediated hepatocyte apoptosis via the TGR5-FOSL1 pathway.

Cellular and molecular gastroenterology and hepatology·2026
Same author

Role of nitrate-dependent Fe(II)-oxidizing bacteria in coupling nitrogen and phosphorus cycling in nearshore sediments of shallow lakes.

Water research·2026
Same author

Biomimetic ferroelectric-semiconductor transistor enables neuronal multisensory integration.

Nature communications·2026
Same author

Nickel-Catalyzed Fourfold Cascade Cage BH Arylation of <i>o</i>-Carboranes.

Inorganic chemistry·2026
Same author

Accurate alpha-particle stopping power measurements in graphenic carbon foils and their application to high-precision, non-destructive areal density determination.

Scientific reports·2026
Same author

Tetra-Alkynylation of Cage B(3,4,5,6)-H Bonds in <i>o</i>-Carboranes via Nickel Catalysis.

Organic letters·2026

This study introduces the Low-Rank-Recovery Network (LRRNet) for robust face recognition from incomplete images. LRRNet effectively recovers corrupted images and extracts features for high recognition rates, even in large datasets.

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Image Processing

Background:

  • Traditional face recognition methods struggle with incomplete or corrupted images common in real-world applications.
  • Existing techniques often fail to achieve high accuracy when significant portions of facial data are missing.

Purpose of the Study:

  • To develop a novel deep learning framework for robust face recognition from incomplete images.
  • To address the limitations of current methods in handling heavily corrupted facial data.

Main Methods:

  • A Low-Rank-Recovery Network (LRRNet) integrating matrix completion and deep learning is proposed.
  • LRRNet recovers incomplete face images using truncated nuclear norm regularization.
  • Low-rank image parts are extracted as filters, processed via binarization and histogram algorithms, and classified using Support Vector Machines (SVMs).
Keywords:
ADMMConvolutional neural networksDeep learningFace recognitionRecovery of low-rank matrix

More Related Videos

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

1.1K

Related Experiment Videos

Last Updated: Feb 25, 2026

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

10.1K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

1.1K

Main Results:

  • The LRRNet achieves a high face recognition rate, particularly for heavily corrupted images.
  • The method demonstrates superior performance and efficiency, especially within large-scale facial databases.
  • Experimental results show LRRNet outperforms other robust face recognition techniques on benchmark datasets.

Conclusions:

  • LRRNet offers an effective solution for face recognition challenges posed by incomplete and corrupted image data.
  • The proposed framework provides a robust and efficient approach for real-world face recognition systems.
  • The study highlights the potential of combining matrix completion with deep learning for enhanced image analysis.