Search

  • Select Article Type
  • Abstract Supplements
  • Blood Group Review
  • Call to Arms
  • Hypothesis
  • In Memoriam
  • Interview
  • Introduction
  • Short Report
  • abstract
  • Abstracts
  • Article
  • book-review
  • case-report
  • case-study
  • Clinical Practice
  • Commentary
  • Conference Presentation
  • conference-report
  • congress-report
  • Correction
  • critical-appraisal
  • Editorial
  • Editorial Comment
  • Erratum
  • Events
  • Letter
  • Letter to Editor
  • mini-review
  • minireview
  • News
  • non-scientific
  • Obituary
  • original-paper
  • original-report
  • Original Research
  • Pictorial Review
  • Position Paper
  • Practice Report
  • Preface
  • Preliminary report
  • Product Review
  • rapid-communication
  • Report
  • research-article
  • Research Communicate
  • research-paper
  • Research Report
  • Review
  • review -article
  • review-article
  • review-paper
  • Review Paper
  • Sampling Methods
  • Scientific Commentary
  • short-communication
  • short-report
  • Student Essay
  • Varia
  • Welome
  • Select Journal
  • International Journal Advanced Network Monitoring Controls

 

Article | 30-November-2020

Deep Periocular Recognition Method via Multi-Angle Data Augmentation

recognition based on lightweight convolutional neural network model is feasible. The same method is used to test the test set. The test set samples are rotated from multiple angles to test the robustness of the model. After the rotation of the test set, the model is still able to be recognized normally. The accuracy of the IncpetionV3 network model test is 98. 5%, and the MobileNetV2 lightweight model test is 98. 4%. TABLE VIII. COMPARISON OF INCPETION V3 AND MOBILENET V2 METHODS Methods

Bo Liu, Songze Lei, Yonggang Li, Aokui Shan, Baihua Dong

International Journal of Advanced Network, Monitoring and Controls, Volume 6 , ISSUE 1, 11–17

No Record Found..
Page Actions